import os import re import unicodedata import diff...
創建於:2026年1月11日
使用 GPT-5.2 Thinking 回答 Chat01
創建於:2026年1月11日
使用 GPT-5.2 Thinking 回答 Chat01
import os
import re
import unicodedata
import difflib
import pandas as pd
from collections import deque, defaultdict, Counter
from sympy import symbols, Eq, solve
from datetime import datetime, timedelta
from openpyxl import Workbook, load_workbook
from openpyxl.styles import Alignment, Font, PatternFill, Border, Side
from openpyxl.utils import get_column_letter
excel_file_path = r"C:\Users\User\Desktop\results\results.xlsx"
league_thresholds = {
"Albania Superiore": (2.52, 2.73),
"Andorra Primera": (2.42, 2.75),
"Armenia Premier": (2.32, 3.20),
"Bosnia WWin Liga": (2.00, 3.20),
"Croatia HNL": (2.29, 3.25),
"Cyprus League": (2.25, 3.20),
"Cyprus Division 2": (2.46, 2.70),
"Czech Chance Liga": (2.25, 3.30),
"Denmark Superliga": (2.40, 3.00),
"Greece Super League": (2.36, 3.40),
"Greece Super League 2": (2.25, 3.30),
"Hungary OTP Bank Liga": (2.17, 3.40),
"Hungary Merkantil Bank Liga": (2.38, 3.30),
"Luxembourg BGL Ligue": (2.20, 3.00),
"Malta Premier League": (2.75, 2.60),
"Montenegro Prva Liga": (2.50, 3.20),
"North Macedonia 1 MFL": (2.13, 3.60),
"Slovakia Nike Liga": (2.30, 3.00),
"Slovenia Prva Liga": (2.47, 3.00),
"Algeria Ligue 2": (1.87, 5.00),
"Mexico Liga de Expansion MX": (2.00, 4.00),
"South Africa Premiership": (2.31, 3.45),
"Croatia Prva NL": (2.40, 2.80),
"India ISL": (2.17, 3.33),
"Indonesia Liga 1": (2.27, 3.45),
"Bulgaria Vtora liga": (2.27, 3.45),
"Zambia Super League": (2.47, 3.10),
"Romania Liga 3": (2.30, 2.94),
"Myanmar National League": (2.50, 2.50),
"Tanzania Ligi Kuu Bara": (2.20, 3.30),
"France Nacional": (2.32, 3.30),
"Nigeria NPFL": (1.50, 6.00),
"Turkey 1.Lig": (2.27, 3.20),
"Algeria Ligue 1": (2.05, 4.30),
"Italy Serie C - A": (2.38, 3.30),
"Italy Serie B": (2.46, 3.50),
"Algeria Ligue 2 - 21": (2.00, 3.20),
"England National League South": (2.38, 3.00),
"Brazil Paulista A4": (2.44, 3.00),
"Ethiopia": (3.12, 2.85),
"Spain LaLiga": (2.29, 3.61),
"Australia NPL": (2.22, 3.00),
"Bulgaria Vtora Liga": (2.08, 3.70),
"Italy Serie C - C": (2.40, 3.20),
"Spain Segunda": (2.11, 4.02),
"France Ligue 1": (2.30, 3.60),
"Brazil Serie A": (2.05, 4.00),
"Brazil Serie B": (2.05, 4.00),
"Brazil Serie C": (2.15, 3.70),
"Iceland Besta Delid": (2.12, 3.10),
"Australia NPL Northern": (2.47, 2.30),
"Norway Division 2": (2.08, 2.94),
"USA MLS": (2.27, 3.20),
"Argentina": (2.22, 3.80),
"Mexico": (2.08, 3.80),
"Bundesliga - 2": (2.16, 3.55),
"France - 2": (2.16, 3.55),
"Netherlands - Eridivisie": (2.20, 3.20),
"England - Premier League": (2.18, 3.60)
}
def normalize_dashes(text):
if isinstance(text, str):
return text.replace('–', '-').replace('—', '-').replace('−', '-')
return text
def clean_team_name(name):
if isinstance(name, str):
name = normalize_dashes(name)
return ' '.join(name.strip().split())
return name
def sanitize_pair_text(p):
if not isinstance(p, str):
return p
p = p.strip()
p = normalize_dashes(p)
p = re.sub(r"\s*->\s*&\s*[A-Za-z]:[\/].*", "", p)
p = re.sub(r"\s*&\s*[A-Za-z]:[\\/].*", "", p)
return p.strip()
def parse_date_to_dt(raw_date):
if isinstance(raw_date, datetime):
return raw_date
if isinstance(raw_date, (float, int)):
try:
return datetime(1899, 12, 30) + timedelta(days=int(raw_date))
except:
return None
if isinstance(raw_date, str):
try:
if ' - ' in raw_date:
date_part = raw_date.split(' - ')[0].strip()
return datetime.strptime(date_part, '%d.%m.%Y')
return datetime.strptime(raw_date.strip(), '%d.%m.%Y')
except:
return None
return None
def to_float(x):
return float(str(x).replace(',', '.'))
def fmt2(x) -> str:
try:
return f"{to_float(x):.2f}"
except:
return str(x)
def strip_accents(s: str) -> str:
s = unicodedata.normalize("NFKD", s)
return "".join(ch for ch in s if not unicodedata.combining(ch))
ORG_TOKENS = {
"fc","cf","ad","cd","ud","sc","ac","afc","fk","sk","nk","as","ss","sv","if","bk","kf",
"cfc","fcd","f.c","c.f","a.d","u.d","c.d","s.c","a.c",
"club","clube","clubs","football","futbol","fútbol","calcio"
}
CONNECTOR_TOKENS = {
"de","del","la","las","los","el","da","do","di","du","der","den","van","von","the","of","and"
}
ABBREV_MAP = {
"dep": "deportivo",
"depor": "deportivo",
}
def canonical_team_key(name: str) -> str:
if not isinstance(name, str):
return ""
s = clean_team_name(name)
s = strip_accents(s.lower())
s = re.sub(r"[^0-9a-z\s]", " ", s)
tokens = [t for t in s.split() if t]
textnormalized = [] for t in tokens: t = ABBREV_MAP.get(t, t) if t in ORG_TOKENS: continue if t in CONNECTOR_TOKENS: continue normalized.append(t) if not normalized: normalized = tokens return " ".join(normalized).strip()
def key_tokens(key: str):
return [t for t in key.split() if t]
def match_score_by_tokens(user_key: str, rep_key: str) -> float:
if not user_key or not rep_key:
return 0.0
u_toks = set(key_tokens(user_key))
r_toks = set(key_tokens(rep_key))
if not u_toks or not r_toks:
return 0.0
textinter = len(u_toks & r_toks) if inter == 0: return 0.0 containment = inter / min(len(u_toks), len(r_toks)) # подмножество токенов dice = (2 * inter) / (len(u_toks) + len(r_toks)) seq = difflib.SequenceMatcher(None, user_key, rep_key).ratio() return max(seq, dice, 0.98 * containment)
def build_team_normalization_maps(raw_rows):
key_to_counts = defaultdict(Counter)
textfor league, date, home, away, o1, ox, o2 in raw_rows: kh = canonical_team_key(home) ka = canonical_team_key(away) if kh: key_to_counts[kh][home] += 1 if ka: key_to_counts[ka][away] += 1 rep_by_key = {} alias_to_rep = {} for key, cnt in key_to_counts.items(): most = cnt.most_common() max_count = most[0][1] candidates = [name for name, c in most if c == max_count] rep = min(candidates, key=lambda x: (len(x), x.lower())) rep_by_key[key] = rep for name in cnt.keys(): alias_to_rep[name] = rep rep_names = set(rep_by_key.values()) rep_key_by_name = {rep: canonical_team_key(rep) for rep in rep_names} return rep_by_key, alias_to_rep, rep_names, rep_key_by_name
def resolve_user_team_name(
user_name: str,
alias_to_rep,
rep_by_key,
rep_names,
rep_key_by_name,
fuzzy_min_ratio=0.84,
ambiguity_eps=0.02,
margin=0.08
):
cleaned = clean_team_name(user_name)
if cleaned in rep_names:
return cleaned, None
textif cleaned in alias_to_rep: return alias_to_rep[cleaned], None key = canonical_team_key(cleaned) if key in rep_by_key: rep = rep_by_key[key] if rep != cleaned: return rep, f"Нормализация: '{cleaned}' -> '{rep}'" return rep, None scored = [] for rep in rep_names: rep_key = rep_key_by_name.get(rep, "") score = match_score_by_tokens(key, rep_key) if score > 0: scored.append((score, rep)) if not scored: return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." scored.sort(reverse=True, key=lambda x: x[0]) best_score, best_rep = scored[0] second_score = scored[1][0] if len(scored) > 1 else 0.0 near_best = [rep for sc, rep in scored if sc >= best_score - ambiguity_eps] if len(near_best) > 1 and best_score < 0.95: return cleaned, ( f"ВНИМАНИЕ: '{cleaned}' неоднозначно (ключ='{key}'), возможные варианты: " f"{', '.join(near_best[:6])}" + (" ..." if len(near_best) > 6 else "") ) if best_score >= fuzzy_min_ratio and (best_score >= 0.95 or (best_score - second_score) >= margin): return best_rep, f"Fuzzy/token-нормализация: '{cleaned}' -> '{best_rep}' (score={best_score:.2f})" return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')."
def split_pair_robust(p: str):
p = normalize_dashes(p)
if " - " in p:
a, b = p.split(" - ", 1)
return a.strip(), b.strip()
textparts = re.split(r"\s+[-]\s+", p) if len(parts) == 2: return parts[0].strip(), parts[1].strip() parts2 = re.split(r"\s*-\s*", p) if len(parts2) == 2: return parts2[0].strip(), parts2[1].strip() return None
def line_compact(s: str) -> str:
s = normalize_dashes(str(s))
s = re.sub(r"\s+", " ", s).strip()
return s
def signature_from_chain_base_lines(base_lines):
# base_lines = ["date | home-away", ...]
return "\n".join(line_compact(x) for x in base_lines)
def signature_from_matches_cell(text):
if not text:
return ""
lines = []
for ln in str(text).splitlines():
ln = normalize_dashes(ln).strip()
ln = re.sub(r"\s*\s*$", "", ln).strip() # убрать (odds)
ln = re.sub(r"\s+", " ", ln).strip()
if ln:
lines.append(ln)
return "\n".join(lines)
df = pd.read_excel(excel_file_path)
raw_rows = []
for _, row in df.iterrows():
league = row[0]
date = row[1]
home = clean_team_name(row[2])
away = clean_team_name(row[3])
odds1 = row[4]
odds_draw = row[5]
odds2 = row[6]
raw_rows.append((league, date, home, away, odds1, odds_draw, odds2))
rep_by_key, alias_to_rep, rep_names, rep_key_by_name = build_team_normalization_maps(raw_rows)
matches = []
for league, date, home, away, odds1, odds_draw, odds2 in raw_rows:
home_rep = alias_to_rep.get(home, home)
away_rep = alias_to_rep.get(away, away)
matches.append((league, date, home_rep, away_rep, odds1, odds_draw, odds2))
def find_chains(matches, start_team, end_team, min_depth=1, max_depth=3):
graph = {}
for match in matches:
league, date, home_team, away_team, odds1, odds_draw, odds2 = match
graph.setdefault(home_team, [])
graph.setdefault(away_team, [])
graph[home_team].append((away_team, match))
graph[away_team].append((home_team, match))
textchains = [] queue = deque([(start_team, [], set())]) while queue: current_team, path, visited = queue.popleft() if current_team == end_team and path: if min_depth <= len(path) <= max_depth: chains.append(path) continue if len(path) >= max_depth: continue for neighbor, match in graph.get(current_team, []): if match not in visited: new_visited = visited.copy() new_visited.add(match) queue.append((neighbor, path + [match], new_visited)) return chains
raw_input_teams = input(
"Введите либо 2 команды (как раньше), либо список пар через запятую.\n"
"Пример: Malaga - Granada, Granada - Albacete\n"
"Можно использовать '-', '–' или '—'.\n"
"Ввод: "
).strip()
raw_input_teams = sanitize_pair_text(raw_input_teams)
team_pairs = []
has_any_dash = '-' in raw_input_teams
if (',' in raw_input_teams) or has_any_dash:
parts = [p.strip() for p in re.split(r"[,\n;]+", raw_input_teams) if p.strip()]
for p in parts:
p = sanitize_pair_text(p)
if not p:
continue
textsp = split_pair_robust(p) if not sp: print(f"Пропуск (неверный формат пары, нужен 'Команда1 - Команда2'): {p}") continue a, b = sp a = clean_team_name(a) b = clean_team_name(b) if a and b: team_pairs.append((a, b)) if not team_pairs: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)]
else:
start_team = clean_team_name(raw_input_teams)
end_team = clean_team_name(input("Введите название команды назначения: ").strip())
team_pairs = [(start_team, end_team)]
resolved_pairs = []
for a, b in team_pairs:
ra, wa = resolve_user_team_name(a, alias_to_rep, rep_by_key, rep_names, rep_key_by_name)
rb, wb = resolve_user_team_name(b, alias_to_rep, rep_by_key, rep_names, rep_key_by_name)
if wa:
print(wa)
if wb:
print(wb)
resolved_pairs.append((ra, rb))
team_pairs = resolved_pairs
class TeamStrengthCalculator:
def init(self):
self.games = []
self.equations_method_2 = []
self.teams = set()
textdef add_games(self, games): for g in games: league, date, home_team, away_team, home_odds, draw_odds, away_odds = g self.games.append({ 'league': league, 'date': date, 'home_team': clean_team_name(home_team), 'away_team': clean_team_name(away_team), 'home_odds': to_float(home_odds), 'draw_odds': to_float(draw_odds), 'away_odds': to_float(away_odds) }) self.teams.add(clean_team_name(home_team)) self.teams.add(clean_team_name(away_team)) def calculate_strength_difference_method_2(self): for game in self.games: league_name = game['league'] home_team = game['home_team'] away_team = game['away_team'] home_odds = game['home_odds'] away_odds = game['away_odds'] threshold_home, threshold_away = league_thresholds.get(league_name, (2.40, 3.00)) if home_odds < away_odds: if home_odds < threshold_home: home_strength = abs((100 / threshold_home) - (100 / home_odds)) self.equations_method_2.append( f"{home_team} = {away_team} + {home_strength:.3f}" ) else: home_strength = abs((100 / home_odds) - (100 / threshold_home)) self.equations_method_2.append( f"{away_team} = {home_team} + {home_strength:.3f}" ) else: if away_odds < threshold_away: away_strength = abs((100 / threshold_away) - (100 / away_odds)) self.equations_method_2.append( f"{away_team} = {home_team} + {away_strength:.3f}" ) else: away_strength = abs((100 / away_odds) - (100 / threshold_away)) self.equations_method_2.append( f"{home_team} = {away_team} + {away_strength:.3f}" ) def _safe_sympy_symbol(self, team: str): base = canonical_team_key(team).replace(" ", "_") base = re.sub(r"[^0-9a-zA-Z_]", "_", base) if not base: base = "team" if base[0].isdigit(): base = "t_" + base return symbols(base) def simplify_with_sympy_method2(self, start_team, end_team): if not self.games: return "", ["Нет матчей для расчета."], ("", "") first_league = self.games[0]['league'] threshold_home, threshold_away = league_thresholds.get(first_league, (2.40, 3.00)) team_symbols = {} for team in self.teams: if team == start_team: team_symbols[team] = 0 else: team_symbols[team] = self._safe_sympy_symbol(team) sympy_equations = [] for equation in self.equations_method_2: parts = equation.split('=') if len(parts) == 2 and '+' in parts[1]: left_team, right = parts[0].strip(), parts[1].strip() right_team, strength_diff = right.split('+') right_team = right_team.strip() strength_diff = float(strength_diff.strip()) left_sym = team_symbols[left_team] right_sym = team_symbols[right_team] sympy_equations.append(Eq(left_sym, right_sym + strength_diff)) symbols_list = [sym for sym in team_symbols.values() if sym != 0] solution = solve(sympy_equations, symbols_list, dict=True) if sympy_equations else [] end_symbol = team_symbols.get(end_team) if not solution or end_symbol is None: return "", ["Нет решения для метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") sol = solution[0] if end_symbol not in sol: return "", [f"Команда {end_team} не найдена в решении метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") try: end_value_numeric = float(sol[end_symbol].evalf()) except Exception: return "", [f"Не удалось вычислить численное значение силы {end_team} в методе 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") strength_diff = -end_value_numeric new_odds_start = 100 / ((100 / threshold_home) + strength_diff) new_odds_end = 100 / ((100 / threshold_home) - strength_diff) method2_str = ( f"{start_team} = {end_team} + {strength_diff:.3f}; " f"{start_team} odds = {new_odds_start:.3f}; {end_team} odds = {new_odds_end:.3f}" ) return method2_str, [], (f"{threshold_home:.2f}", f"{threshold_away:.2f}")
thin = Side(style="thin", color="000000")
medium = Side(style="medium", color="000000")
BORDER_THIN = Border(left=thin, right=thin, top=thin, bottom=thin)
BORDER_MEDIUM_TOP = Border(left=thin, right=thin, top=medium, bottom=thin)
ALIGN_WRAP_TOP = Alignment(wrap_text=True, vertical="top")
ALIGN_CENTER = Alignment(horizontal="center", vertical="center", wrap_text=True)
FONT_HEADER = Font(bold=True, size=11)
FONT_BOLD = Font(bold=True)
FONT_MONO = Font(name="Consolas")
FILL_HEADER = PatternFill("solid", fgColor="D9E1F2")
FILL_PAIR = PatternFill("solid", fgColor="E2EFDA")
FILL_NEW_CHAIN = PatternFill("solid", fgColor="FFF2CC") # жёлтый
FILL_NONE = PatternFill() # без заливки
EXPECTED_HEADERS = [
"RUN",
"Request #",
"Start",
"End",
"Th home",
"Th away",
"Avg Date",
"Matches (Date | Home-Away (1,X,2))",
"Result"
]
def init_results_workbook(output_excel_path):
if os.path.exists(output_excel_path):
wb = load_workbook(output_excel_path)
else:
wb = Workbook()
textif "Results" in wb.sheetnames: ws = wb["Results"] else: ws = wb.active ws.title = "Results" if ws.max_row == 1 and ws["A1"].value is None: ws.append(EXPECTED_HEADERS) else: current = [ws.cell(row=1, column=i).value for i in range(1, len(EXPECTED_HEADERS) + 1)] if current != EXPECTED_HEADERS: base = "Results_v2" name = base i = 2 while name in wb.sheetnames: name = f"{base}_{i}" i += 1 ws = wb.create_sheet(name) ws.append(EXPECTED_HEADERS) for col in range(1, len(EXPECTED_HEADERS) + 1): c = ws.cell(row=1, column=col) c.font = FONT_HEADER c.fill = FILL_HEADER c.alignment = ALIGN_CENTER c.border = BORDER_THIN widths = [18, 9, 18, 18, 9, 9, 11, 70, 55] for i, w in enumerate(widths, start=1): ws.column_dimensions[get_column_letter(i)].width = w ws.freeze_panes = "A2" return wb, ws
def apply_row_style(ws, r, is_pair_first_row: bool, is_new_chain: bool):
for col in range(1, len(EXPECTED_HEADERS) + 1):
cell = ws.cell(row=r, column=col)
cell.alignment = ALIGN_WRAP_TOP
cell.border = BORDER_MEDIUM_TOP if is_pair_first_row else BORDER_THIN
text# Сначала чистим заливку, потом накладываем нужную cell.fill = FILL_NONE # Подсветка новых цепочек — приоритетнее if is_new_chain: cell.fill = FILL_NEW_CHAIN else: # Подсветка пары (как было) только на первой строке блока и только B,C,D if is_pair_first_row and col in (2, 3, 4): cell.fill = FILL_PAIR # Fonts if is_pair_first_row and col in (2, 3, 4): cell.font = FONT_BOLD elif col == 8: cell.font = FONT_MONO else: cell.font = Font() # default
def set_row_height_from_matches(ws, r, matches_text):
matches_text = str(matches_text) if matches_text else ""
line_count = matches_text.count("\n") + 1
ws.row_dimensions[r].height = min(max(18, 14 * line_count), 260)
def append_row(ws, row_values, is_new_pair=False, is_new_chain=False):
ws.append(row_values)
r = ws.max_row
apply_row_style(ws, r, is_new_pair, is_new_chain)
set_row_height_from_matches(ws, r, row_values[7])
def find_last_segment_for_pair(ws, start_team: str, end_team: str):
"""
Ищем последний (самый нижний) непрерывный блок строк, где Start/End совпадают.
Возвращает (seg_start, seg_end) или None.
"""
start_col = 3 # C
end_col = 4 # D
textsegments = [] in_seg = False seg_start = None for r in range(2, ws.max_row + 1): s = ws.cell(row=r, column=start_col).value e = ws.cell(row=r, column=end_col).value s = clean_team_name(s) if s else "" e = clean_team_name(e) if e else "" if s == start_team and e == end_team: if not in_seg: in_seg = True seg_start = r else: if in_seg: segments.append((seg_start, r - 1)) in_seg = False seg_start = None if in_seg: segments.append((seg_start, ws.max_row)) if not segments: return None return segments[-1]
run_dt = datetime.now()
run_stamp = run_dt.strftime("%d.%m.%Y %H:%M:%S")
out_dir = os.path.dirname(excel_file_path) if os.path.dirname(excel_file_path) else os.getcwd()
output_excel_path = os.path.join(out_dir, "wtp_results.xlsx")
wb, ws = init_results_workbook(output_excel_path)
for request_num, (start_team, end_team) in enumerate(team_pairs, start=1):
chains = find_chains(matches, start_team, end_team)
text# убрать дубликаты цепочек (по матчам) unique_chains = [] seen = set() for ch in chains: t = tuple(ch) if t not in seen: seen.add(t) unique_chains.append(ch) chains = unique_chains # ---- формируем desired_rows: список строк, которые должны быть в Excel для этой пары ---- desired_rows = [] if not chains: desired_rows.append({ "signature": "", "values": [run_stamp, request_num, start_team, end_team, "", "", "", "", ""] }) else: # группировка по длине, сортировка по средней дате (свежие сверху) groups = {} for chain in chains: L = len(chain) groups.setdefault(L, []) dts = [parse_date_to_dt(m[1]) for m in chain] dts = [d for d in dts if d] avg_date = datetime.fromtimestamp(sum(d.timestamp() for d in dts) / len(dts)) if dts else datetime.min groups[L].append({"chain": chain, "avg_date": avg_date}) for L in groups: groups[L] = sorted(groups[L], key=lambda x: x["avg_date"], reverse=True) for L in sorted(groups.keys()): for info in groups[L]: chain = info["chain"] avg_date = info["avg_date"] avg_date_str = avg_date.strftime("%d.%m.%Y") if avg_date != datetime.min else "" games = [] base_lines = [] used_league_for_threshold = None for match in chain: league, date, home, away, o1, ox, o2 = match games.append(match) if used_league_for_threshold is None: used_league_for_threshold = league base_lines.append(f"{date} | {home}-{away}") # signature без odds (чтобы совпадало даже если odds обновились) chain_sig = signature_from_chain_base_lines(base_lines) # красивый вывод с выравниванием скобок (как было) max_base_len = max(len(b) for b in base_lines) if base_lines else 0 matches_lines_for_excel = [] for base, match in zip(base_lines, chain): _, date, home, away, o1, ox, o2 = match pad_spaces = " " * (max_base_len - len(base) + 2) matches_lines_for_excel.append( f"{base}{pad_spaces}({fmt2(o1)}, {fmt2(ox)}, {fmt2(o2)})" ) th_home, th_away = league_thresholds.get(used_league_for_threshold, (2.40, 3.00)) th_home_str = f"{th_home:.2f}" th_away_str = f"{th_away:.2f}" calc = TeamStrengthCalculator() calc.add_games(games) calc.calculate_strength_difference_method_2() result2, warnings, _ths = calc.simplify_with_sympy_method2(start_team, end_team) desired_rows.append({ "signature": chain_sig, "values": [ run_stamp, # RUN request_num, # Request # start_team, # Start end_team, # End th_home_str, # Th home th_away_str, # Th away avg_date_str, # Avg Date "\n".join(matches_lines_for_excel), # Matches result2 # Result ] }) # ---- обновляем существующий блок для пары (или добавляем новый) ---- seg = find_last_segment_for_pair(ws, start_team, end_team) if seg is None: # пары ещё нет в файле — просто добавляем блок (без жёлтого) first = True for item in desired_rows: append_row(ws, item["values"], is_new_pair=first, is_new_chain=False) first = False continue seg_start, seg_end = seg current_len = seg_end - seg_start + 1 desired_len = len(desired_rows) # существующие signatures (по текущему блоку) existing_sigs = set() for r in range(seg_start, seg_end + 1): sig = signature_from_matches_cell(ws.cell(row=r, column=8).value) # H existing_sigs.add(sig) # подгоняем размер блока под desired_len if desired_len > current_len: insert_at = seg_end + 1 ws.insert_rows(insert_at, amount=(desired_len - current_len)) seg_end += (desired_len - current_len) elif desired_len < current_len: delete_from = seg_start + desired_len ws.delete_rows(delete_from, amount=(current_len - desired_len)) seg_end = seg_start + desired_len - 1 # перезаписываем строки блока for i, item in enumerate(desired_rows): r = seg_start + i vals = item["values"] sig = item["signature"] is_pair_first_row = (i == 0) # новая цепочка — если ее сигнатуры не было раньше (и сигнатура не пустая) is_new_chain = (sig != "" and sig not in existing_sigs) # записываем значения for col_idx, v in enumerate(vals, start=1): ws.cell(row=r, column=col_idx, value=v) # применяем стили apply_row_style(ws, r, is_pair_first_row, is_new_chain) set_row_height_from_matches(ws, r, vals[7])
wb.save(output_excel_path)
print(f"\nГотово. Результаты обновлены в Excel:\n{output_excel_path}") изучи этот код, он работает идеально, но кое-что нужно поменять, когда он загружает данные в excel я хотел бы чтобы он в цепочках помечал кое-какие команды определенным цветом чтобы они выделялись, допустим при запуске кода я ввел: Castellon – Leganes, Ceuta – Valladolid, Cultural Leonesa – Gijon, Zaragoza – Real Sociedad B, Almeria – Dep. La Coruna, Mirandes – Andorra, Racing Santander – Las Palmas, Albacete – Cadiz CF, Burgos CF – Huesca, Cordoba – Malaga, Granada CF – Eibar код выдал мне определенные результаты, вот кусочек допустим:
04.01.2026 - 00:15 | Castellon-Huesca (1.48, 4.31, 7.75)
21.12.2025 - 00:15 | Huesca-Racing Santander (2.66, 3.23, 2.88)
14.12.2025 - 02:30 | Racing Santander-Leganes (1.65, 4.34, 5.01) как ты видишь когда я вводил список команд при запуске кода то написал Castellon – Leganes первой игрой, и первая комнада здесь это Castellon, значит она играет дома а Леганес в гостях, так вот, во всех найденных цйепочках там где Castellon дома он должен быть как-то выделен, а в ценпочках где Leganes в гостях тоже должен быть выделен, цепочки могут быть разные в какой-то только castellon дома в какой-то только Leganes в гостях, в каких-то и Castellon как положено дома и леганес тожде в готстях, надеюсь ты меня понял что нужно делать, это относится ко всем цеочкам и ко всем командам, измени код и вышли мне полный исправленный код
pythonimport openpyxl, sys, pkgutil, openpyxl openpyxl.__version__ '3.1.5'
pythonfrom openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont CellRichText, TextBlock, InlineFont (openpyxl.cell.rich_text.CellRichText, openpyxl.cell.rich_text.TextBlock, openpyxl.cell.text.InlineFont)
pythonfrom openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont rt = CellRichText([TextBlock(InlineFont(b=True), "Hello"), TextBlock(InlineFont(), "\nWorld")]) rt CellRichText([TextBlock text=Hello, font=<openpyxl.cell.text.InlineFont object> Parameters: rFont=None, charset=None, family=None, b=True, i=False, strike=None, outline=None, shadow=None, condense=None, extend=None, color=None, sz=None, u=None, vertAlign=None, scheme=None, TextBlock text= World, font=default])
pythondir(rt)[:30], hasattr(rt, "plain"), hasattr(rt, "text") (['__add__', '__class__', '__class_getitem__', '__contains__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__getstate__', '__gt__', '__hash__', '__iadd__', '__imul__', '__init__', '__init_subclass__', '__iter__', '__le__', '__len__', '__lt__', '__module__', '__mul__', '__ne__', '__new__', '__reduce__'], False, False)
pythonfrom openpyxl.cell.text import InlineFont f=InlineFont(rFont="Consolas", color="00B050", b=True) f.color <openpyxl.styles.colors.Color object> Parameters: rgb='0000B050', indexed=None, auto=None, theme=None, tint=0.0, type='rgb'
pythonupdated_code = r""" import os import re import unicodedata import difflib import pandas as pd from collections import deque, defaultdict, Counter from sympy import symbols, Eq, solve from datetime import datetime, timedelta from openpyxl import Workbook, load_workbook from openpyxl.styles import Alignment, Font, PatternFill, Border, Side from openpyxl.utils import get_column_letter # ✅ NEW: Rich text support (font colors inside a single cell) from openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont # ===================== НАСТРОЙКИ ===================== excel_file_path = r"C:\Users\User\Desktop\results\results.xlsx" # ===================================================== league_thresholds = { "Albania Superiore": (2.52, 2.73), "Andorra Primera": (2.42, 2.75), "Armenia Premier": (2.32, 3.20), "Bosnia WWin Liga": (2.00, 3.20), "Croatia HNL": (2.29, 3.25), "Cyprus League": (2.25, 3.20), "Cyprus Division 2": (2.46, 2.70), "Czech Chance Liga": (2.25, 3.30), "Denmark Superliga": (2.40, 3.00), "Greece Super League": (2.36, 3.40), "Greece Super League 2": (2.25, 3.30), "Hungary OTP Bank Liga": (2.17, 3.40), "Hungary Merkantil Bank Liga": (2.38, 3.30), "Luxembourg BGL Ligue": (2.20, 3.00), "Malta Premier League": (2.75, 2.60), "Montenegro Prva Liga": (2.50, 3.20), "North Macedonia 1 MFL": (2.13, 3.60), "Slovakia Nike Liga": (2.30, 3.00), "Slovenia Prva Liga": (2.47, 3.00), "Algeria Ligue 2": (1.87, 5.00), "Mexico Liga de Expansion MX": (2.00, 4.00), "South Africa Premiership": (2.31, 3.45), "Croatia Prva NL": (2.40, 2.80), "India ISL": (2.17, 3.33), "Indonesia Liga 1": (2.27, 3.45), "Bulgaria Vtora liga": (2.27, 3.45), "Zambia Super League": (2.47, 3.10), "Romania Liga 3": (2.30, 2.94), "Myanmar National League": (2.50, 2.50), "Tanzania Ligi Kuu Bara": (2.20, 3.30), "France Nacional": (2.32, 3.30), "Nigeria NPFL": (1.50, 6.00), "Turkey 1.Lig": (2.27, 3.20), "Algeria Ligue 1": (2.05, 4.30), "Italy Serie C - A": (2.38, 3.30), "Italy Serie B": (2.46, 3.50), "Algeria Ligue 2 - 21": (2.00, 3.20), "England National League South": (2.38, 3.00), "Brazil Paulista A4": (2.44, 3.00), "Ethiopia": (3.12, 2.85), "Spain LaLiga": (2.29, 3.61), "Australia NPL": (2.22, 3.00), "Bulgaria Vtora Liga": (2.08, 3.70), "Italy Serie C - C": (2.40, 3.20), "Spain Segunda": (2.11, 4.02), "France Ligue 1": (2.30, 3.60), "Brazil Serie A": (2.05, 4.00), "Brazil Serie B": (2.05, 4.00), "Brazil Serie C": (2.15, 3.70), "Iceland Besta Delid": (2.12, 3.10), "Australia NPL Northern": (2.47, 2.30), "Norway Division 2": (2.08, 2.94), "USA MLS": (2.27, 3.20), "Argentina": (2.22, 3.80), "Mexico": (2.08, 3.80), "Bundesliga - 2": (2.16, 3.55), "France - 2": (2.16, 3.55), "Netherlands - Eridivisie": (2.20, 3.20), "England - Premier League": (2.18, 3.60) } # ===================== helpers ===================== def normalize_dashes(text): if isinstance(text, str): return text.replace('–', '-').replace('—', '-').replace('−', '-') return text def clean_team_name(name): if isinstance(name, str): name = normalize_dashes(name) return ' '.join(name.strip().split()) return name def sanitize_pair_text(p): if not isinstance(p, str): return p p = p.strip() p = normalize_dashes(p) p = re.sub(r"\s*->\s*&\s*[A-Za-z]:[\\/].*$", "", p) p = re.sub(r"\s*&\s*[A-Za-z]:[\\/].*$", "", p) return p.strip() def parse_date_to_dt(raw_date): if isinstance(raw_date, datetime): return raw_date if isinstance(raw_date, (float, int)): try: return datetime(1899, 12, 30) + timedelta(days=int(raw_date)) except: return None if isinstance(raw_date, str): try: if ' - ' in raw_date: date_part = raw_date.split(' - ')[0].strip() return datetime.strptime(date_part, '%d.%m.%Y') return datetime.strptime(raw_date.strip(), '%d.%m.%Y') except: return None return None def to_float(x): return float(str(x).replace(',', '.')) def fmt2(x) -> str: try: return f"{to_float(x):.2f}" except: return str(x) def strip_accents(s: str) -> str: s = unicodedata.normalize("NFKD", s) return "".join(ch for ch in s if not unicodedata.combining(ch)) ORG_TOKENS = { "fc","cf","ad","cd","ud","sc","ac","afc","fk","sk","nk","as","ss","sv","if","bk","kf", "cfc","fcd","f.c","c.f","a.d","u.d","c.d","s.c","a.c", "club","clube","clubs","football","futbol","fútbol","calcio" } CONNECTOR_TOKENS = { "de","del","la","las","los","el","da","do","di","du","der","den","van","von","the","of","and" } ABBREV_MAP = { "dep": "deportivo", "depor": "deportivo", } def canonical_team_key(name: str) -> str: if not isinstance(name, str): return "" s = clean_team_name(name) s = strip_accents(s.lower()) s = re.sub(r"[^0-9a-z\s]", " ", s) tokens = [t for t in s.split() if t] normalized = [] for t in tokens: t = ABBREV_MAP.get(t, t) if t in ORG_TOKENS: continue if t in CONNECTOR_TOKENS: continue normalized.append(t) if not normalized: normalized = tokens return " ".join(normalized).strip() def key_tokens(key: str): return [t for t in key.split() if t] def match_score_by_tokens(user_key: str, rep_key: str) -> float: if not user_key or not rep_key: return 0.0 u_toks = set(key_tokens(user_key)) r_toks = set(key_tokens(rep_key)) if not u_toks or not r_toks: return 0.0 inter = len(u_toks & r_toks) if inter == 0: return 0.0 containment = inter / min(len(u_toks), len(r_toks)) # подмножество токенов dice = (2 * inter) / (len(u_toks) + len(r_toks)) seq = difflib.SequenceMatcher(None, user_key, rep_key).ratio() return max(seq, dice, 0.98 * containment) def build_team_normalization_maps(raw_rows): key_to_counts = defaultdict(Counter) for league, date, home, away, o1, ox, o2 in raw_rows: kh = canonical_team_key(home) ka = canonical_team_key(away) if kh: key_to_counts[kh][home] += 1 if ka: key_to_counts[ka][away] += 1 rep_by_key = {} alias_to_rep = {} for key, cnt in key_to_counts.items(): most = cnt.most_common() max_count = most[0][1] candidates = [name for name, c in most if c == max_count] rep = min(candidates, key=lambda x: (len(x), x.lower())) rep_by_key[key] = rep for name in cnt.keys(): alias_to_rep[name] = rep rep_names = set(rep_by_key.values()) rep_key_by_name = {rep: canonical_team_key(rep) for rep in rep_names} return rep_by_key, alias_to_rep, rep_names, rep_key_by_name def resolve_user_team_name( user_name: str, alias_to_rep, rep_by_key, rep_names, rep_key_by_name, fuzzy_min_ratio=0.84, ambiguity_eps=0.02, margin=0.08 ): cleaned = clean_team_name(user_name) if cleaned in rep_names: return cleaned, None if cleaned in alias_to_rep: return alias_to_rep[cleaned], None key = canonical_team_key(cleaned) if key in rep_by_key: rep = rep_by_key[key] if rep != cleaned: return rep, f"Нормализация: '{cleaned}' -> '{rep}'" return rep, None scored = [] for rep in rep_names: rep_key = rep_key_by_name.get(rep, "") score = match_score_by_tokens(key, rep_key) if score > 0: scored.append((score, rep)) if not scored: return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." scored.sort(reverse=True, key=lambda x: x[0]) best_score, best_rep = scored[0] second_score = scored[1][0] if len(scored) > 1 else 0.0 near_best = [rep for sc, rep in scored if sc >= best_score - ambiguity_eps] if len(near_best) > 1 and best_score < 0.95: return cleaned, ( f"ВНИМАНИЕ: '{cleaned}' неоднозначно (ключ='{key}'), возможные варианты: " f"{', '.join(near_best[:6])}" + (" ..." if len(near_best) > 6 else "") ) if best_score >= fuzzy_min_ratio and (best_score >= 0.95 or (best_score - second_score) >= margin): return best_rep, f"Fuzzy/token-нормализация: '{cleaned}' -> '{best_rep}' (score={best_score:.2f})" return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." def split_pair_robust(p: str): p = normalize_dashes(p) if " - " in p: a, b = p.split(" - ", 1) return a.strip(), b.strip() parts = re.split(r"\s+[-]\s+", p) if len(parts) == 2: return parts[0].strip(), parts[1].strip() parts2 = re.split(r"\s*-\s*", p) if len(parts2) == 2: return parts2[0].strip(), parts2[1].strip() return None # ===== signatures (чтобы не плодить дубликаты цепочек) ===== def line_compact(s: str) -> str: s = normalize_dashes(str(s)) s = re.sub(r"\s+", " ", s).strip() return s def signature_from_chain_base_lines(base_lines): # base_lines = ["date | home-away", ...] return "\n".join(line_compact(x) for x in base_lines) # ✅ NEW: safe conversion for RichText -> str (для высоты строк и сигнатур) def _plain_text(value) -> str: if value is None: return "" if isinstance(value, CellRichText): return "".join(tb.text for tb in value) return str(value) def signature_from_matches_cell(text): if not text: return "" text = _plain_text(text) lines = [] for ln in str(text).splitlines(): ln = normalize_dashes(ln).strip() # ✅ FIX/IMPROVE: реально убираем " (odds)" в конце строки (чтобы сигнатура совпадала даже при обновлении odds) ln = re.sub(r"\s*$[^)]*$\s*$", "", ln).strip() ln = re.sub(r"\s+", " ", ln).strip() if ln: lines.append(ln) return "\n".join(lines) # ===================== RichText coloring for teams ===================== # Настрой цвета/стиля тут: INLINE_MONO = InlineFont(rFont="Consolas") # обычный текст INLINE_HOME_HL = InlineFont(rFont="Consolas", b=True, color="1F4E79") # стартовая команда (HOME) — тёмно-синий INLINE_AWAY_HL = InlineFont(rFont="Consolas", b=True, color="9C0006") # конечная команда (AWAY) — тёмно-красный def build_matches_rich_text(chain, start_team, end_team): """ Возвращает CellRichText для колонки 'Matches', где: - start_team подсвечивается, если он стоит ДОМА (home) в строке - end_team подсвечивается, если он стоит В ГОСТЯХ (away) в строке """ base_lines = [f"{m[1]} | {m[2]}-{m[3]}" for m in chain] max_base_len = max((len(b) for b in base_lines), default=0) blocks = [] for idx, match in enumerate(chain): _league, date, home, away, o1, ox, o2 = match base = f"{date} | {home}-{away}" pad_spaces = " " * (max_base_len - len(base) + 2) odds_str = f"({fmt2(o1)}, {fmt2(ox)}, {fmt2(o2)})" # date + " | " blocks.append(TextBlock(INLINE_MONO, f"{date} | ")) # home team (highlight only if it's exactly start_team and is HOME) blocks.append(TextBlock(INLINE_HOME_HL if home == start_team else INLINE_MONO, str(home))) # dash blocks.append(TextBlock(INLINE_MONO, "-")) # away team (highlight only if it's exactly end_team and is AWAY) blocks.append(TextBlock(INLINE_AWAY_HL if away == end_team else INLINE_MONO, str(away))) # padding + odds blocks.append(TextBlock(INLINE_MONO, f"{pad_spaces}{odds_str}")) if idx != len(chain) - 1: blocks.append(TextBlock(INLINE_MONO, "\n")) return CellRichText(blocks) # ===================== read matches ===================== df = pd.read_excel(excel_file_path) raw_rows = [] for _, row in df.iterrows(): league = row[0] date = row[1] home = clean_team_name(row[2]) away = clean_team_name(row[3]) odds1 = row[4] odds_draw = row[5] odds2 = row[6] raw_rows.append((league, date, home, away, odds1, odds_draw, odds2)) rep_by_key, alias_to_rep, rep_names, rep_key_by_name = build_team_normalization_maps(raw_rows) matches = [] for league, date, home, away, odds1, odds_draw, odds2 in raw_rows: home_rep = alias_to_rep.get(home, home) away_rep = alias_to_rep.get(away, away) matches.append((league, date, home_rep, away_rep, odds1, odds_draw, odds2)) # ===================== chains ===================== def find_chains(matches, start_team, end_team, min_depth=1, max_depth=3): graph = {} for match in matches: league, date, home_team, away_team, odds1, odds_draw, odds2 = match graph.setdefault(home_team, []) graph.setdefault(away_team, []) graph[home_team].append((away_team, match)) graph[away_team].append((home_team, match)) chains = [] queue = deque([(start_team, [], set())]) while queue: current_team, path, visited = queue.popleft() if current_team == end_team and path: if min_depth <= len(path) <= max_depth: chains.append(path) continue if len(path) >= max_depth: continue for neighbor, match in graph.get(current_team, []): if match not in visited: new_visited = visited.copy() new_visited.add(match) queue.append((neighbor, path + [match], new_visited)) return chains # ===================== input pairs ===================== raw_input_teams = input( "Введите либо 2 команды (как раньше), либо список пар через запятую.\n" "Пример: Malaga - Granada, Granada - Albacete\n" "Можно использовать '-', '–' или '—'.\n" "Ввод: " ).strip() raw_input_teams = sanitize_pair_text(raw_input_teams) team_pairs = [] has_any_dash = '-' in raw_input_teams if (',' in raw_input_teams) or has_any_dash: parts = [p.strip() for p in re.split(r"[,\n;]+", raw_input_teams) if p.strip()] for p in parts: p = sanitize_pair_text(p) if not p: continue sp = split_pair_robust(p) if not sp: print(f"Пропуск (неверный формат пары, нужен 'Команда1 - Команда2'): {p}") continue a, b = sp a = clean_team_name(a) b = clean_team_name(b) if a and b: team_pairs.append((a, b)) if not team_pairs: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] else: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] resolved_pairs = [] for a, b in team_pairs: ra, wa = resolve_user_team_name(a, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) rb, wb = resolve_user_team_name(b, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) if wa: print(wa) if wb: print(wb) resolved_pairs.append((ra, rb)) team_pairs = resolved_pairs # ===================== calculator ===================== class TeamStrengthCalculator: def __init__(self): self.games = [] self.equations_method_2 = [] self.teams = set() def add_games(self, games): for g in games: league, date, home_team, away_team, home_odds, draw_odds, away_odds = g self.games.append({ 'league': league, 'date': date, 'home_team': clean_team_name(home_team), 'away_team': clean_team_name(away_team), 'home_odds': to_float(home_odds), 'draw_odds': to_float(draw_odds), 'away_odds': to_float(away_odds) }) self.teams.add(clean_team_name(home_team)) self.teams.add(clean_team_name(away_team)) def calculate_strength_difference_method_2(self): for game in self.games: league_name = game['league'] home_team = game['home_team'] away_team = game['away_team'] home_odds = game['home_odds'] away_odds = game['away_odds'] threshold_home, threshold_away = league_thresholds.get(league_name, (2.40, 3.00)) if home_odds < away_odds: if home_odds < threshold_home: home_strength = abs((100 / threshold_home) - (100 / home_odds)) self.equations_method_2.append( f"{home_team} = {away_team} + {home_strength:.3f}" ) else: home_strength = abs((100 / home_odds) - (100 / threshold_home)) self.equations_method_2.append( f"{away_team} = {home_team} + {home_strength:.3f}" ) else: if away_odds < threshold_away: away_strength = abs((100 / threshold_away) - (100 / away_odds)) self.equations_method_2.append( f"{away_team} = {home_team} + {away_strength:.3f}" ) else: away_strength = abs((100 / away_odds) - (100 / threshold_away)) self.equations_method_2.append( f"{home_team} = {away_team} + {away_strength:.3f}" ) def _safe_sympy_symbol(self, team: str): base = canonical_team_key(team).replace(" ", "_") base = re.sub(r"[^0-9a-zA-Z_]", "_", base) if not base: base = "team" if base[0].isdigit(): base = "t_" + base return symbols(base) def simplify_with_sympy_method2(self, start_team, end_team): if not self.games: return "", ["Нет матчей для расчета."], ("", "") first_league = self.games[0]['league'] threshold_home, threshold_away = league_thresholds.get(first_league, (2.40, 3.00)) team_symbols = {} for team in self.teams: if team == start_team: team_symbols[team] = 0 else: team_symbols[team] = self._safe_sympy_symbol(team) sympy_equations = [] for equation in self.equations_method_2: parts = equation.split('=') if len(parts) == 2 and '+' in parts[1]: left_team, right = parts[0].strip(), parts[1].strip() right_team, strength_diff = right.split('+') right_team = right_team.strip() strength_diff = float(strength_diff.strip()) left_sym = team_symbols[left_team] right_sym = team_symbols[right_team] sympy_equations.append(Eq(left_sym, right_sym + strength_diff)) symbols_list = [sym for sym in team_symbols.values() if sym != 0] solution = solve(sympy_equations, symbols_list, dict=True) if sympy_equations else [] end_symbol = team_symbols.get(end_team) if not solution or end_symbol is None: return "", ["Нет решения для метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") sol = solution[0] if end_symbol not in sol: return "", [f"Команда {end_team} не найдена в решении метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") try: end_value_numeric = float(sol[end_symbol].evalf()) except Exception: return "", [f"Не удалось вычислить численное значение силы {end_team} в методе 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") strength_diff = -end_value_numeric new_odds_start = 100 / ((100 / threshold_home) + strength_diff) new_odds_end = 100 / ((100 / threshold_home) - strength_diff) method2_str = ( f"{start_team} = {end_team} + {strength_diff:.3f}; " f"{start_team} odds = {new_odds_start:.3f}; {end_team} odds = {new_odds_end:.3f}" ) return method2_str, [], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") # ===================== Excel styles ===================== thin = Side(style="thin", color="000000") medium = Side(style="medium", color="000000") BORDER_THIN = Border(left=thin, right=thin, top=thin, bottom=thin) BORDER_MEDIUM_TOP = Border(left=thin, right=thin, top=medium, bottom=thin) ALIGN_WRAP_TOP = Alignment(wrap_text=True, vertical="top") ALIGN_CENTER = Alignment(horizontal="center", vertical="center", wrap_text=True) FONT_HEADER = Font(bold=True, size=11) FONT_BOLD = Font(bold=True) FONT_MONO = Font(name="Consolas") FILL_HEADER = PatternFill("solid", fgColor="D9E1F2") FILL_PAIR = PatternFill("solid", fgColor="E2EFDA") FILL_NEW_CHAIN = PatternFill("solid", fgColor="FFF2CC") # жёлтый FILL_NONE = PatternFill() # без заливки EXPECTED_HEADERS = [ "RUN", "Request #", "Start", "End", "Th home", "Th away", "Avg Date", "Matches (Date | Home-Away (1,X,2))", "Result" ] def init_results_workbook(output_excel_path): if os.path.exists(output_excel_path): wb = load_workbook(output_excel_path) else: wb = Workbook() if "Results" in wb.sheetnames: ws = wb["Results"] else: ws = wb.active ws.title = "Results" if ws.max_row == 1 and ws["A1"].value is None: ws.append(EXPECTED_HEADERS) else: current = [ws.cell(row=1, column=i).value for i in range(1, len(EXPECTED_HEADERS) + 1)] if current != EXPECTED_HEADERS: base = "Results_v2" name = base i = 2 while name in wb.sheetnames: name = f"{base}_{i}" i += 1 ws = wb.create_sheet(name) ws.append(EXPECTED_HEADERS) for col in range(1, len(EXPECTED_HEADERS) + 1): c = ws.cell(row=1, column=col) c.font = FONT_HEADER c.fill = FILL_HEADER c.alignment = ALIGN_CENTER c.border = BORDER_THIN widths = [18, 9, 18, 18, 9, 9, 11, 70, 55] for i, w in enumerate(widths, start=1): ws.column_dimensions[get_column_letter(i)].width = w ws.freeze_panes = "A2" return wb, ws def apply_row_style(ws, r, is_pair_first_row: bool, is_new_chain: bool): for col in range(1, len(EXPECTED_HEADERS) + 1): cell = ws.cell(row=r, column=col) cell.alignment = ALIGN_WRAP_TOP cell.border = BORDER_MEDIUM_TOP if is_pair_first_row else BORDER_THIN # Сначала чистим заливку, потом накладываем нужную cell.fill = FILL_NONE # Подсветка новых цепочек — приоритетнее if is_new_chain: cell.fill = FILL_NEW_CHAIN else: # Подсветка пары (как было) только на первой строке блока и только B,C,D if is_pair_first_row and col in (2, 3, 4): cell.fill = FILL_PAIR # Fonts if is_pair_first_row and col in (2, 3, 4): cell.font = FONT_BOLD elif col == 8: cell.font = FONT_MONO else: cell.font = Font() # default def set_row_height_from_matches(ws, r, matches_text): matches_text = _plain_text(matches_text) line_count = matches_text.count("\n") + 1 if matches_text else 1 ws.row_dimensions[r].height = min(max(18, 14 * line_count), 260) def append_row(ws, row_values, is_new_pair=False, is_new_chain=False): ws.append(row_values) r = ws.max_row apply_row_style(ws, r, is_new_pair, is_new_chain) set_row_height_from_matches(ws, r, row_values[7]) def find_last_segment_for_pair(ws, start_team: str, end_team: str): """ Ищем последний (самый нижний) непрерывный блок строк, где Start/End совпадают. Возвращает (seg_start, seg_end) или None. """ start_col = 3 # C end_col = 4 # D segments = [] in_seg = False seg_start = None for r in range(2, ws.max_row + 1): s = ws.cell(row=r, column=start_col).value e = ws.cell(row=r, column=end_col).value s = clean_team_name(s) if s else "" e = clean_team_name(e) if e else "" if s == start_team and e == end_team: if not in_seg: in_seg = True seg_start = r else: if in_seg: segments.append((seg_start, r - 1)) in_seg = False seg_start = None if in_seg: segments.append((seg_start, ws.max_row)) if not segments: return None return segments[-1] # ===================== MAIN ===================== run_dt = datetime.now() run_stamp = run_dt.strftime("%d.%m.%Y %H:%M:%S") out_dir = os.path.dirname(excel_file_path) if os.path.dirname(excel_file_path) else os.getcwd() output_excel_path = os.path.join(out_dir, "wtp_results.xlsx") wb, ws = init_results_workbook(output_excel_path) for request_num, (start_team, end_team) in enumerate(team_pairs, start=1): chains = find_chains(matches, start_team, end_team) # убрать дубликаты цепочек (по матчам) unique_chains = [] seen = set() for ch in chains: t = tuple(ch) if t not in seen: seen.add(t) unique_chains.append(ch) chains = unique_chains # ---- формируем desired_rows: список строк, которые должны быть в Excel для этой пары ---- desired_rows = [] if not chains: desired_rows.append({ "signature": "", "values": [run_stamp, request_num, start_team, end_team, "", "", "", "", ""] }) else: # группировка по длине, сортировка по средней дате (свежие сверху) groups = {} for chain in chains: L = len(chain) groups.setdefault(L, []) dts = [parse_date_to_dt(m[1]) for m in chain] dts = [d for d in dts if d] avg_date = datetime.fromtimestamp(sum(d.timestamp() for d in dts) / len(dts)) if dts else datetime.min groups[L].append({"chain": chain, "avg_date": avg_date}) for L in groups: groups[L] = sorted(groups[L], key=lambda x: x["avg_date"], reverse=True) for L in sorted(groups.keys()): for info in groups[L]: chain = info["chain"] avg_date = info["avg_date"] avg_date_str = avg_date.strftime("%d.%m.%Y") if avg_date != datetime.min else "" games = [] base_lines = [] used_league_for_threshold = None for match in chain: league, date, home, away, o1, ox, o2 = match games.append(match) if used_league_for_threshold is None: used_league_for_threshold = league base_lines.append(f"{date} | {home}-{away}") # signature без odds (чтобы совпадало даже если odds обновились) chain_sig = signature_from_chain_base_lines(base_lines) # ✅ NEW: rich text (подсветка start_team как HOME и end_team как AWAY) matches_cell_value = build_matches_rich_text(chain, start_team, end_team) th_home, th_away = league_thresholds.get(used_league_for_threshold, (2.40, 3.00)) th_home_str = f"{th_home:.2f}" th_away_str = f"{th_away:.2f}" calc = TeamStrengthCalculator() calc.add_games(games) calc.calculate_strength_difference_method_2() result2, warnings, _ths = calc.simplify_with_sympy_method2(start_team, end_team) desired_rows.append({ "signature": chain_sig, "values": [ run_stamp, # RUN request_num, # Request # start_team, # Start end_team, # End th_home_str, # Th home th_away_str, # Th away avg_date_str, # Avg Date matches_cell_value, # Matches (RichText) result2 # Result ] }) # ---- обновляем существующий блок для пары (или добавляем новый) ---- seg = find_last_segment_for_pair(ws, start_team, end_team) if seg is None: # пары ещё нет в файле — просто добавляем блок (без жёлтого) first = True for item in desired_rows: append_row(ws, item["values"], is_new_pair=first, is_new_chain=False) first = False continue seg_start, seg_end = seg current_len = seg_end - seg_start + 1 desired_len = len(desired_rows) # существующие signatures (по текущему блоку) existing_sigs = set() for r in range(seg_start, seg_end + 1): sig = signature_from_matches_cell(ws.cell(row=r, column=8).value) # H existing_sigs.add(sig) # подгоняем размер блока под desired_len if desired_len > current_len: insert_at = seg_end + 1 ws.insert_rows(insert_at, amount=(desired_len - current_len)) seg_end += (desired_len - current_len) elif desired_len < current_len: delete_from = seg_start + desired_len ws.delete_rows(delete_from, amount=(current_len - desired_len)) seg_end = seg_start + desired_len - 1 # перезаписываем строки блока for i, item in enumerate(desired_rows): r = seg_start + i vals = item["values"] sig = item["signature"] is_pair_first_row = (i == 0) # новая цепочка — если ее сигнатуры не было раньше (и сигнатура не пустая) is_new_chain = (sig != "" and sig not in existing_sigs) # записываем значения for col_idx, v in enumerate(vals, start=1): ws.cell(row=r, column=col_idx, value=v) # применяем стили apply_row_style(ws, r, is_pair_first_row, is_new_chain) set_row_height_from_matches(ws, r, vals[7]) wb.save(output_excel_path) print(f"\nГотово. Результаты обновлены в Excel:\n{output_excel_path}") """ import ast, textwrap ast.parse(updated_code) len(updated_code.splitlines())
pythonupdated_code = ''' import os import re import unicodedata import difflib import pandas as pd from collections import deque, defaultdict, Counter from sympy import symbols, Eq, solve from datetime import datetime, timedelta from openpyxl import Workbook, load_workbook from openpyxl.styles import Alignment, Font, PatternFill, Border, Side from openpyxl.utils import get_column_letter # ✅ NEW: Rich text support (font colors inside a single cell) from openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont # ===================== НАСТРОЙКИ ===================== excel_file_path = r"C:\\Users\\User\\Desktop\\results\\results.xlsx" # ===================================================== league_thresholds = { "Albania Superiore": (2.52, 2.73), "Andorra Primera": (2.42, 2.75), "Armenia Premier": (2.32, 3.20), "Bosnia WWin Liga": (2.00, 3.20), "Croatia HNL": (2.29, 3.25), "Cyprus League": (2.25, 3.20), "Cyprus Division 2": (2.46, 2.70), "Czech Chance Liga": (2.25, 3.30), "Denmark Superliga": (2.40, 3.00), "Greece Super League": (2.36, 3.40), "Greece Super League 2": (2.25, 3.30), "Hungary OTP Bank Liga": (2.17, 3.40), "Hungary Merkantil Bank Liga": (2.38, 3.30), "Luxembourg BGL Ligue": (2.20, 3.00), "Malta Premier League": (2.75, 2.60), "Montenegro Prva Liga": (2.50, 3.20), "North Macedonia 1 MFL": (2.13, 3.60), "Slovakia Nike Liga": (2.30, 3.00), "Slovenia Prva Liga": (2.47, 3.00), "Algeria Ligue 2": (1.87, 5.00), "Mexico Liga de Expansion MX": (2.00, 4.00), "South Africa Premiership": (2.31, 3.45), "Croatia Prva NL": (2.40, 2.80), "India ISL": (2.17, 3.33), "Indonesia Liga 1": (2.27, 3.45), "Bulgaria Vtora liga": (2.27, 3.45), "Zambia Super League": (2.47, 3.10), "Romania Liga 3": (2.30, 2.94), "Myanmar National League": (2.50, 2.50), "Tanzania Ligi Kuu Bara": (2.20, 3.30), "France Nacional": (2.32, 3.30), "Nigeria NPFL": (1.50, 6.00), "Turkey 1.Lig": (2.27, 3.20), "Algeria Ligue 1": (2.05, 4.30), "Italy Serie C - A": (2.38, 3.30), "Italy Serie B": (2.46, 3.50), "Algeria Ligue 2 - 21": (2.00, 3.20), "England National League South": (2.38, 3.00), "Brazil Paulista A4": (2.44, 3.00), "Ethiopia": (3.12, 2.85), "Spain LaLiga": (2.29, 3.61), "Australia NPL": (2.22, 3.00), "Bulgaria Vtora Liga": (2.08, 3.70), "Italy Serie C - C": (2.40, 3.20), "Spain Segunda": (2.11, 4.02), "France Ligue 1": (2.30, 3.60), "Brazil Serie A": (2.05, 4.00), "Brazil Serie B": (2.05, 4.00), "Brazil Serie C": (2.15, 3.70), "Iceland Besta Delid": (2.12, 3.10), "Australia NPL Northern": (2.47, 2.30), "Norway Division 2": (2.08, 2.94), "USA MLS": (2.27, 3.20), "Argentina": (2.22, 3.80), "Mexico": (2.08, 3.80), "Bundesliga - 2": (2.16, 3.55), "France - 2": (2.16, 3.55), "Netherlands - Eridivisie": (2.20, 3.20), "England - Premier League": (2.18, 3.60) } # ===================== helpers ===================== def normalize_dashes(text): if isinstance(text, str): return text.replace('–', '-').replace('—', '-').replace('−', '-') return text def clean_team_name(name): if isinstance(name, str): name = normalize_dashes(name) return ' '.join(name.strip().split()) return name def sanitize_pair_text(p): if not isinstance(p, str): return p p = p.strip() p = normalize_dashes(p) p = re.sub(r"\\s*->\\s*&\\s*[A-Za-z]:[\\\\/].*$", "", p) p = re.sub(r"\\s*&\\s*[A-Za-z]:[\\\\/].*$", "", p) return p.strip() def parse_date_to_dt(raw_date): if isinstance(raw_date, datetime): return raw_date if isinstance(raw_date, (float, int)): try: return datetime(1899, 12, 30) + timedelta(days=int(raw_date)) except: return None if isinstance(raw_date, str): try: if ' - ' in raw_date: date_part = raw_date.split(' - ')[0].strip() return datetime.strptime(date_part, '%d.%m.%Y') return datetime.strptime(raw_date.strip(), '%d.%m.%Y') except: return None return None def to_float(x): return float(str(x).replace(',', '.')) def fmt2(x) -> str: try: return f"{to_float(x):.2f}" except: return str(x) def strip_accents(s: str) -> str: s = unicodedata.normalize("NFKD", s) return "".join(ch for ch in s if not unicodedata.combining(ch)) ORG_TOKENS = { "fc","cf","ad","cd","ud","sc","ac","afc","fk","sk","nk","as","ss","sv","if","bk","kf", "cfc","fcd","f.c","c.f","a.d","u.d","c.d","s.c","a.c", "club","clube","clubs","football","futbol","fútbol","calcio" } CONNECTOR_TOKENS = { "de","del","la","las","los","el","da","do","di","du","der","den","van","von","the","of","and" } ABBREV_MAP = { "dep": "deportivo", "depor": "deportivo", } def canonical_team_key(name: str) -> str: if not isinstance(name, str): return "" s = clean_team_name(name) s = strip_accents(s.lower()) s = re.sub(r"[^0-9a-z\\s]", " ", s) tokens = [t for t in s.split() if t] normalized = [] for t in tokens: t = ABBREV_MAP.get(t, t) if t in ORG_TOKENS: continue if t in CONNECTOR_TOKENS: continue normalized.append(t) if not normalized: normalized = tokens return " ".join(normalized).strip() def key_tokens(key: str): return [t for t in key.split() if t] def match_score_by_tokens(user_key: str, rep_key: str) -> float: if not user_key or not rep_key: return 0.0 u_toks = set(key_tokens(user_key)) r_toks = set(key_tokens(rep_key)) if not u_toks or not r_toks: return 0.0 inter = len(u_toks & r_toks) if inter == 0: return 0.0 containment = inter / min(len(u_toks), len(r_toks)) # подмножество токенов dice = (2 * inter) / (len(u_toks) + len(r_toks)) seq = difflib.SequenceMatcher(None, user_key, rep_key).ratio() return max(seq, dice, 0.98 * containment) def build_team_normalization_maps(raw_rows): key_to_counts = defaultdict(Counter) for league, date, home, away, o1, ox, o2 in raw_rows: kh = canonical_team_key(home) ka = canonical_team_key(away) if kh: key_to_counts[kh][home] += 1 if ka: key_to_counts[ka][away] += 1 rep_by_key = {} alias_to_rep = {} for key, cnt in key_to_counts.items(): most = cnt.most_common() max_count = most[0][1] candidates = [name for name, c in most if c == max_count] rep = min(candidates, key=lambda x: (len(x), x.lower())) rep_by_key[key] = rep for name in cnt.keys(): alias_to_rep[name] = rep rep_names = set(rep_by_key.values()) rep_key_by_name = {rep: canonical_team_key(rep) for rep in rep_names} return rep_by_key, alias_to_rep, rep_names, rep_key_by_name def resolve_user_team_name( user_name: str, alias_to_rep, rep_by_key, rep_names, rep_key_by_name, fuzzy_min_ratio=0.84, ambiguity_eps=0.02, margin=0.08 ): cleaned = clean_team_name(user_name) if cleaned in rep_names: return cleaned, None if cleaned in alias_to_rep: return alias_to_rep[cleaned], None key = canonical_team_key(cleaned) if key in rep_by_key: rep = rep_by_key[key] if rep != cleaned: return rep, f"Нормализация: '{cleaned}' -> '{rep}'" return rep, None scored = [] for rep in rep_names: rep_key = rep_key_by_name.get(rep, "") score = match_score_by_tokens(key, rep_key) if score > 0: scored.append((score, rep)) if not scored: return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." scored.sort(reverse=True, key=lambda x: x[0]) best_score, best_rep = scored[0] second_score = scored[1][0] if len(scored) > 1 else 0.0 near_best = [rep for sc, rep in scored if sc >= best_score - ambiguity_eps] if len(near_best) > 1 and best_score < 0.95: return cleaned, ( f"ВНИМАНИЕ: '{cleaned}' неоднозначно (ключ='{key}'), возможные варианты: " f"{', '.join(near_best[:6])}" + (" ..." if len(near_best) > 6 else "") ) if best_score >= fuzzy_min_ratio and (best_score >= 0.95 or (best_score - second_score) >= margin): return best_rep, f"Fuzzy/token-нормализация: '{cleaned}' -> '{best_rep}' (score={best_score:.2f})" return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." def split_pair_robust(p: str): p = normalize_dashes(p) if " - " in p: a, b = p.split(" - ", 1) return a.strip(), b.strip() parts = re.split(r"\\s+[-]\\s+", p) if len(parts) == 2: return parts[0].strip(), parts[1].strip() parts2 = re.split(r"\\s*-\\s*", p) if len(parts2) == 2: return parts2[0].strip(), parts2[1].strip() return None # ===== signatures (чтобы не плодить дубликаты цепочек) ===== def line_compact(s: str) -> str: s = normalize_dashes(str(s)) s = re.sub(r"\\s+", " ", s).strip() return s def signature_from_chain_base_lines(base_lines): # base_lines = ["date | home-away", ...] return "\\n".join(line_compact(x) for x in base_lines) # ✅ NEW: safe conversion for RichText -> str (для высоты строк и сигнатур) def _plain_text(value) -> str: if value is None: return "" if isinstance(value, CellRichText): return "".join(tb.text for tb in value) return str(value) def signature_from_matches_cell(text): if not text: return "" text = _plain_text(text) lines = [] for ln in str(text).splitlines(): ln = normalize_dashes(ln).strip() # ✅ реально убираем " (odds)" в конце строки (чтобы сигнатура совпадала даже при обновлении odds) ln = re.sub(r"\\s*\$[^)]*\$\\s*$", "", ln).strip() ln = re.sub(r"\\s+", " ", ln).strip() if ln: lines.append(ln) return "\\n".join(lines) # ===================== RichText coloring for teams ===================== # Настрой цвета/стиля тут: INLINE_MONO = InlineFont(rFont="Consolas") # обычный текст INLINE_HOME_HL = InlineFont(rFont="Consolas", b=True, color="1F4E79") # стартовая команда (HOME) — тёмно-синий INLINE_AWAY_HL = InlineFont(rFont="Consolas", b=True, color="9C0006") # конечная команда (AWAY) — тёмно-красный def build_matches_rich_text(chain, start_team, end_team): """ Возвращает CellRichText для колонки 'Matches', где: - start_team подсвечивается, если он стоит ДОМА (home) в строке - end_team подсвечивается, если он стоит В ГОСТЯХ (away) в строке """ base_lines = [f"{m[1]} | {m[2]}-{m[3]}" for m in chain] max_base_len = max((len(b) for b in base_lines), default=0) blocks = [] for idx, match in enumerate(chain): _league, date, home, away, o1, ox, o2 = match base = f"{date} | {home}-{away}" pad_spaces = " " * (max_base_len - len(base) + 2) odds_str = f"({fmt2(o1)}, {fmt2(ox)}, {fmt2(o2)})" blocks.append(TextBlock(INLINE_MONO, f"{date} | ")) blocks.append(TextBlock(INLINE_HOME_HL if home == start_team else INLINE_MONO, str(home))) blocks.append(TextBlock(INLINE_MONO, "-")) blocks.append(TextBlock(INLINE_AWAY_HL if away == end_team else INLINE_MONO, str(away))) blocks.append(TextBlock(INLINE_MONO, f"{pad_spaces}{odds_str}")) if idx != len(chain) - 1: blocks.append(TextBlock(INLINE_MONO, "\\n")) return CellRichText(blocks) # ===================== read matches ===================== df = pd.read_excel(excel_file_path) raw_rows = [] for _, row in df.iterrows(): league = row[0] date = row[1] home = clean_team_name(row[2]) away = clean_team_name(row[3]) odds1 = row[4] odds_draw = row[5] odds2 = row[6] raw_rows.append((league, date, home, away, odds1, odds_draw, odds2)) rep_by_key, alias_to_rep, rep_names, rep_key_by_name = build_team_normalization_maps(raw_rows) matches = [] for league, date, home, away, odds1, odds_draw, odds2 in raw_rows: home_rep = alias_to_rep.get(home, home) away_rep = alias_to_rep.get(away, away) matches.append((league, date, home_rep, away_rep, odds1, odds_draw, odds2)) # ===================== chains ===================== def find_chains(matches, start_team, end_team, min_depth=1, max_depth=3): graph = {} for match in matches: league, date, home_team, away_team, odds1, odds_draw, odds2 = match graph.setdefault(home_team, []) graph.setdefault(away_team, []) graph[home_team].append((away_team, match)) graph[away_team].append((home_team, match)) chains = [] queue = deque([(start_team, [], set())]) while queue: current_team, path, visited = queue.popleft() if current_team == end_team and path: if min_depth <= len(path) <= max_depth: chains.append(path) continue if len(path) >= max_depth: continue for neighbor, match in graph.get(current_team, []): if match not in visited: new_visited = visited.copy() new_visited.add(match) queue.append((neighbor, path + [match], new_visited)) return chains # ===================== input pairs ===================== raw_input_teams = input( "Введите либо 2 команды (как раньше), либо список пар через запятую.\\n" "Пример: Malaga - Granada, Granada - Albacete\\n" "Можно использовать '-', '–' или '—'.\\n" "Ввод: " ).strip() raw_input_teams = sanitize_pair_text(raw_input_teams) team_pairs = [] has_any_dash = '-' in raw_input_teams if (',' in raw_input_teams) or has_any_dash: parts = [p.strip() for p in re.split(r"[,\\n;]+", raw_input_teams) if p.strip()] for p in parts: p = sanitize_pair_text(p) if not p: continue sp = split_pair_robust(p) if not sp: print(f"Пропуск (неверный формат пары, нужен 'Команда1 - Команда2'): {p}") continue a, b = sp a = clean_team_name(a) b = clean_team_name(b) if a and b: team_pairs.append((a, b)) if not team_pairs: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] else: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] resolved_pairs = [] for a, b in team_pairs: ra, wa = resolve_user_team_name(a, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) rb, wb = resolve_user_team_name(b, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) if wa: print(wa) if wb: print(wb) resolved_pairs.append((ra, rb)) team_pairs = resolved_pairs # ===================== calculator ===================== class TeamStrengthCalculator: def __init__(self): self.games = [] self.equations_method_2 = [] self.teams = set() def add_games(self, games): for g in games: league, date, home_team, away_team, home_odds, draw_odds, away_odds = g self.games.append({ 'league': league, 'date': date, 'home_team': clean_team_name(home_team), 'away_team': clean_team_name(away_team), 'home_odds': to_float(home_odds), 'draw_odds': to_float(draw_odds), 'away_odds': to_float(away_odds) }) self.teams.add(clean_team_name(home_team)) self.teams.add(clean_team_name(away_team)) def calculate_strength_difference_method_2(self): for game in self.games: league_name = game['league'] home_team = game['home_team'] away_team = game['away_team'] home_odds = game['home_odds'] away_odds = game['away_odds'] threshold_home, threshold_away = league_thresholds.get(league_name, (2.40, 3.00)) if home_odds < away_odds: if home_odds < threshold_home: home_strength = abs((100 / threshold_home) - (100 / home_odds)) self.equations_method_2.append( f"{home_team} = {away_team} + {home_strength:.3f}" ) else: home_strength = abs((100 / home_odds) - (100 / threshold_home)) self.equations_method_2.append( f"{away_team} = {home_team} + {home_strength:.3f}" ) else: if away_odds < threshold_away: away_strength = abs((100 / threshold_away) - (100 / away_odds)) self.equations_method_2.append( f"{away_team} = {home_team} + {away_strength:.3f}" ) else: away_strength = abs((100 / away_odds) - (100 / threshold_away)) self.equations_method_2.append( f"{home_team} = {away_team} + {away_strength:.3f}" ) def _safe_sympy_symbol(self, team: str): base = canonical_team_key(team).replace(" ", "_") base = re.sub(r"[^0-9a-zA-Z_]", "_", base) if not base: base = "team" if base[0].isdigit(): base = "t_" + base return symbols(base) def simplify_with_sympy_method2(self, start_team, end_team): if not self.games: return "", ["Нет матчей для расчета."], ("", "") first_league = self.games[0]['league'] threshold_home, threshold_away = league_thresholds.get(first_league, (2.40, 3.00)) team_symbols = {} for team in self.teams: if team == start_team: team_symbols[team] = 0 else: team_symbols[team] = self._safe_sympy_symbol(team) sympy_equations = [] for equation in self.equations_method_2: parts = equation.split('=') if len(parts) == 2 and '+' in parts[1]: left_team, right = parts[0].strip(), parts[1].strip() right_team, strength_diff = right.split('+') right_team = right_team.strip() strength_diff = float(strength_diff.strip()) left_sym = team_symbols[left_team] right_sym = team_symbols[right_team] sympy_equations.append(Eq(left_sym, right_sym + strength_diff)) symbols_list = [sym for sym in team_symbols.values() if sym != 0] solution = solve(sympy_equations, symbols_list, dict=True) if sympy_equations else [] end_symbol = team_symbols.get(end_team) if not solution or end_symbol is None: return "", ["Нет решения для метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") sol = solution[0] if end_symbol not in sol: return "", [f"Команда {end_team} не найдена в решении метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") try: end_value_numeric = float(sol[end_symbol].evalf()) except Exception: return "", [f"Не удалось вычислить численное значение силы {end_team} в методе 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") strength_diff = -end_value_numeric new_odds_start = 100 / ((100 / threshold_home) + strength_diff) new_odds_end = 100 / ((100 / threshold_home) - strength_diff) method2_str = ( f"{start_team} = {end_team} + {strength_diff:.3f}; " f"{start_team} odds = {new_odds_start:.3f}; {end_team} odds = {new_odds_end:.3f}" ) return method2_str, [], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") # ===================== Excel styles ===================== thin = Side(style="thin", color="000000") medium = Side(style="medium", color="000000") BORDER_THIN = Border(left=thin, right=thin, top=thin, bottom=thin) BORDER_MEDIUM_TOP = Border(left=thin, right=thin, top=medium, bottom=thin) ALIGN_WRAP_TOP = Alignment(wrap_text=True, vertical="top") ALIGN_CENTER = Alignment(horizontal="center", vertical="center", wrap_text=True) FONT_HEADER = Font(bold=True, size=11) FONT_BOLD = Font(bold=True) FONT_MONO = Font(name="Consolas") FILL_HEADER = PatternFill("solid", fgColor="D9E1F2") FILL_PAIR = PatternFill("solid", fgColor="E2EFDA") FILL_NEW_CHAIN = PatternFill("solid", fgColor="FFF2CC") # жёлтый FILL_NONE = PatternFill() # без заливки EXPECTED_HEADERS = [ "RUN", "Request #", "Start", "End", "Th home", "Th away", "Avg Date", "Matches (Date | Home-Away (1,X,2))", "Result" ] def init_results_workbook(output_excel_path): if os.path.exists(output_excel_path): wb = load_workbook(output_excel_path) else: wb = Workbook() if "Results" in wb.sheetnames: ws = wb["Results"] else: ws = wb.active ws.title = "Results" if ws.max_row == 1 and ws["A1"].value is None: ws.append(EXPECTED_HEADERS) else: current = [ws.cell(row=1, column=i).value for i in range(1, len(EXPECTED_HEADERS) + 1)] if current != EXPECTED_HEADERS: base = "Results_v2" name = base i = 2 while name in wb.sheetnames: name = f"{base}_{i}" i += 1 ws = wb.create_sheet(name) ws.append(EXPECTED_HEADERS) for col in range(1, len(EXPECTED_HEADERS) + 1): c = ws.cell(row=1, column=col) c.font = FONT_HEADER c.fill = FILL_HEADER c.alignment = ALIGN_CENTER c.border = BORDER_THIN widths = [18, 9, 18, 18, 9, 9, 11, 70, 55] for i, w in enumerate(widths, start=1): ws.column_dimensions[get_column_letter(i)].width = w ws.freeze_panes = "A2" return wb, ws def apply_row_style(ws, r, is_pair_first_row: bool, is_new_chain: bool): for col in range(1, len(EXPECTED_HEADERS) + 1): cell = ws.cell(row=r, column=col) cell.alignment = ALIGN_WRAP_TOP cell.border = BORDER_MEDIUM_TOP if is_pair_first_row else BORDER_THIN # Сначала чистим заливку, потом накладываем нужную cell.fill = FILL_NONE # Подсветка новых цепочек — приоритетнее if is_new_chain: cell.fill = FILL_NEW_CHAIN else: # Подсветка пары (как было) только на первой строке блока и только B,C,D if is_pair_first_row and col in (2, 3, 4): cell.fill = FILL_PAIR # Fonts if is_pair_first_row and col in (2, 3, 4): cell.font = FONT_BOLD elif col == 8: cell.font = FONT_MONO else: cell.font = Font() # default def set_row_height_from_matches(ws, r, matches_text): matches_text = _plain_text(matches_text) line_count = matches_text.count("\\n") + 1 if matches_text else 1 ws.row_dimensions[r].height = min(max(18, 14 * line_count), 260) def append_row(ws, row_values, is_new_pair=False, is_new_chain=False): ws.append(row_values) r = ws.max_row apply_row_style(ws, r, is_new_pair, is_new_chain) set_row_height_from_matches(ws, r, row_values[7]) def find_last_segment_for_pair(ws, start_team: str, end_team: str): """ Ищем последний (самый нижний) непрерывный блок строк, где Start/End совпадают. Возвращает (seg_start, seg_end) или None. """ start_col = 3 # C end_col = 4 # D segments = [] in_seg = False seg_start = None for r in range(2, ws.max_row + 1): s = ws.cell(row=r, column=start_col).value e = ws.cell(row=r, column=end_col).value s = clean_team_name(s) if s else "" e = clean_team_name(e) if e else "" if s == start_team and e == end_team: if not in_seg: in_seg = True seg_start = r else: if in_seg: segments.append((seg_start, r - 1)) in_seg = False seg_start = None if in_seg: segments.append((seg_start, ws.max_row)) if not segments: return None return segments[-1] # ===================== MAIN ===================== run_dt = datetime.now() run_stamp = run_dt.strftime("%d.%m.%Y %H:%M:%S") out_dir = os.path.dirname(excel_file_path) if os.path.dirname(excel_file_path) else os.getcwd() output_excel_path = os.path.join(out_dir, "wtp_results.xlsx") wb, ws = init_results_workbook(output_excel_path) for request_num, (start_team, end_team) in enumerate(team_pairs, start=1): chains = find_chains(matches, start_team, end_team) # убрать дубликаты цепочек (по матчам) unique_chains = [] seen = set() for ch in chains: t = tuple(ch) if t not in seen: seen.add(t) unique_chains.append(ch) chains = unique_chains # ---- формируем desired_rows: список строк, которые должны быть в Excel для этой пары ---- desired_rows = [] if not chains: desired_rows.append({ "signature": "", "values": [run_stamp, request_num, start_team, end_team, "", "", "", "", ""] }) else: # группировка по длине, сортировка по средней дате (свежие сверху) groups = {} for chain in chains: L = len(chain) groups.setdefault(L, []) dts = [parse_date_to_dt(m[1]) for m in chain] dts = [d for d in dts if d] avg_date = datetime.fromtimestamp(sum(d.timestamp() for d in dts) / len(dts)) if dts else datetime.min groups[L].append({"chain": chain, "avg_date": avg_date}) for L in groups: groups[L] = sorted(groups[L], key=lambda x: x["avg_date"], reverse=True) for L in sorted(groups.keys()): for info in groups[L]: chain = info["chain"] avg_date = info["avg_date"] avg_date_str = avg_date.strftime("%d.%m.%Y") if avg_date != datetime.min else "" games = [] base_lines = [] used_league_for_threshold = None for match in chain: league, date, home, away, o1, ox, o2 = match games.append(match) if used_league_for_threshold is None: used_league_for_threshold = league base_lines.append(f"{date} | {home}-{away}") # signature без odds (чтобы совпадало даже если odds обновились) chain_sig = signature_from_chain_base_lines(base_lines) # ✅ RichText (подсветка start_team как HOME и end_team как AWAY) matches_cell_value = build_matches_rich_text(chain, start_team, end_team) th_home, th_away = league_thresholds.get(used_league_for_threshold, (2.40, 3.00)) th_home_str = f"{th_home:.2f}" th_away_str = f"{th_away:.2f}" calc = TeamStrengthCalculator() calc.add_games(games) calc.calculate_strength_difference_method_2() result2, warnings, _ths = calc.simplify_with_sympy_method2(start_team, end_team) desired_rows.append({ "signature": chain_sig, "values": [ run_stamp, # RUN request_num, # Request # start_team, # Start end_team, # End th_home_str, # Th home th_away_str, # Th away avg_date_str, # Avg Date matches_cell_value, # Matches (RichText) result2 # Result ] }) # ---- обновляем существующий блок для пары (или добавляем новый) ---- seg = find_last_segment_for_pair(ws, start_team, end_team) if seg is None: # пары ещё нет в файле — просто добавляем блок (без жёлтого) first = True for item in desired_rows: append_row(ws, item["values"], is_new_pair=first, is_new_chain=False) first = False continue seg_start, seg_end = seg current_len = seg_end - seg_start + 1 desired_len = len(desired_rows) # существующие signatures (по текущему блоку) existing_sigs = set() for r in range(seg_start, seg_end + 1): sig = signature_from_matches_cell(ws.cell(row=r, column=8).value) # H existing_sigs.add(sig) # подгоняем размер блока под desired_len if desired_len > current_len: insert_at = seg_end + 1 ws.insert_rows(insert_at, amount=(desired_len - current_len)) seg_end += (desired_len - current_len) elif desired_len < current_len: delete_from = seg_start + desired_len ws.delete_rows(delete_from, amount=(current_len - desired_len)) seg_end = seg_start + desired_len - 1 # перезаписываем строки блока for i, item in enumerate(desired_rows): r = seg_start + i vals = item["values"] sig = item["signature"] is_pair_first_row = (i == 0) # новая цепочка — если ее сигнатуры не было раньше (и сигнатура не пустая) is_new_chain = (sig != "" and sig not in existing_sigs) # записываем значения for col_idx, v in enumerate(vals, start=1): ws.cell(row=r, column=col_idx, value=v) # применяем стили apply_row_style(ws, r, is_pair_first_row, is_new_chain) set_row_height_from_matches(ws, r, vals[7]) wb.save(output_excel_path) print(f"\\nГотово. Результаты обновлены в Excel:\\n{output_excel_path}") ''' import ast ast.parse(updated_code) len(updated_code.splitlines()) 872
Вот полный исправленный код. Я добавил RichText в колонку Matches, чтобы внутри одной ячейки подсвечивать названием цветом:
Цвета можно поменять в блоке # Настрой цвета/стиля тут:.
pythonimport os import re import unicodedata import difflib import pandas as pd from collections import deque, defaultdict, Counter from sympy import symbols, Eq, solve from datetime import datetime, timedelta from openpyxl import Workbook, load_workbook from openpyxl.styles import Alignment, Font, PatternFill, Border, Side from openpyxl.utils import get_column_letter # ✅ NEW: Rich text support (font colors inside a single cell) from openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont # ===================== НАСТРОЙКИ ===================== excel_file_path = r"C:\Users\User\Desktop\results\results.xlsx" # ===================================================== league_thresholds = { "Albania Superiore": (2.52, 2.73), "Andorra Primera": (2.42, 2.75), "Armenia Premier": (2.32, 3.20), "Bosnia WWin Liga": (2.00, 3.20), "Croatia HNL": (2.29, 3.25), "Cyprus League": (2.25, 3.20), "Cyprus Division 2": (2.46, 2.70), "Czech Chance Liga": (2.25, 3.30), "Denmark Superliga": (2.40, 3.00), "Greece Super League": (2.36, 3.40), "Greece Super League 2": (2.25, 3.30), "Hungary OTP Bank Liga": (2.17, 3.40), "Hungary Merkantil Bank Liga": (2.38, 3.30), "Luxembourg BGL Ligue": (2.20, 3.00), "Malta Premier League": (2.75, 2.60), "Montenegro Prva Liga": (2.50, 3.20), "North Macedonia 1 MFL": (2.13, 3.60), "Slovakia Nike Liga": (2.30, 3.00), "Slovenia Prva Liga": (2.47, 3.00), "Algeria Ligue 2": (1.87, 5.00), "Mexico Liga de Expansion MX": (2.00, 4.00), "South Africa Premiership": (2.31, 3.45), "Croatia Prva NL": (2.40, 2.80), "India ISL": (2.17, 3.33), "Indonesia Liga 1": (2.27, 3.45), "Bulgaria Vtora liga": (2.27, 3.45), "Zambia Super League": (2.47, 3.10), "Romania Liga 3": (2.30, 2.94), "Myanmar National League": (2.50, 2.50), "Tanzania Ligi Kuu Bara": (2.20, 3.30), "France Nacional": (2.32, 3.30), "Nigeria NPFL": (1.50, 6.00), "Turkey 1.Lig": (2.27, 3.20), "Algeria Ligue 1": (2.05, 4.30), "Italy Serie C - A": (2.38, 3.30), "Italy Serie B": (2.46, 3.50), "Algeria Ligue 2 - 21": (2.00, 3.20), "England National League South": (2.38, 3.00), "Brazil Paulista A4": (2.44, 3.00), "Ethiopia": (3.12, 2.85), "Spain LaLiga": (2.29, 3.61), "Australia NPL": (2.22, 3.00), "Bulgaria Vtora Liga": (2.08, 3.70), "Italy Serie C - C": (2.40, 3.20), "Spain Segunda": (2.11, 4.02), "France Ligue 1": (2.30, 3.60), "Brazil Serie A": (2.05, 4.00), "Brazil Serie B": (2.05, 4.00), "Brazil Serie C": (2.15, 3.70), "Iceland Besta Delid": (2.12, 3.10), "Australia NPL Northern": (2.47, 2.30), "Norway Division 2": (2.08, 2.94), "USA MLS": (2.27, 3.20), "Argentina": (2.22, 3.80), "Mexico": (2.08, 3.80), "Bundesliga - 2": (2.16, 3.55), "France - 2": (2.16, 3.55), "Netherlands - Eridivisie": (2.20, 3.20), "England - Premier League": (2.18, 3.60) } # ===================== helpers ===================== def normalize_dashes(text): if isinstance(text, str): return text.replace('–', '-').replace('—', '-').replace('−', '-') return text def clean_team_name(name): if isinstance(name, str): name = normalize_dashes(name) return ' '.join(name.strip().split()) return name def sanitize_pair_text(p): if not isinstance(p, str): return p p = p.strip() p = normalize_dashes(p) p = re.sub(r"\s*->\s*&\s*[A-Za-z]:[\\/].*$", "", p) p = re.sub(r"\s*&\s*[A-Za-z]:[\\/].*$", "", p) return p.strip() def parse_date_to_dt(raw_date): if isinstance(raw_date, datetime): return raw_date if isinstance(raw_date, (float, int)): try: return datetime(1899, 12, 30) + timedelta(days=int(raw_date)) except: return None if isinstance(raw_date, str): try: if ' - ' in raw_date: date_part = raw_date.split(' - ')[0].strip() return datetime.strptime(date_part, '%d.%m.%Y') return datetime.strptime(raw_date.strip(), '%d.%m.%Y') except: return None return None def to_float(x): return float(str(x).replace(',', '.')) def fmt2(x) -> str: try: return f"{to_float(x):.2f}" except: return str(x) def strip_accents(s: str) -> str: s = unicodedata.normalize("NFKD", s) return "".join(ch for ch in s if not unicodedata.combining(ch)) ORG_TOKENS = { "fc","cf","ad","cd","ud","sc","ac","afc","fk","sk","nk","as","ss","sv","if","bk","kf", "cfc","fcd","f.c","c.f","a.d","u.d","c.d","s.c","a.c", "club","clube","clubs","football","futbol","fútbol","calcio" } CONNECTOR_TOKENS = { "de","del","la","las","los","el","da","do","di","du","der","den","van","von","the","of","and" } ABBREV_MAP = { "dep": "deportivo", "depor": "deportivo", } def canonical_team_key(name: str) -> str: if not isinstance(name, str): return "" s = clean_team_name(name) s = strip_accents(s.lower()) s = re.sub(r"[^0-9a-z\s]", " ", s) tokens = [t for t in s.split() if t] normalized = [] for t in tokens: t = ABBREV_MAP.get(t, t) if t in ORG_TOKENS: continue if t in CONNECTOR_TOKENS: continue normalized.append(t) if not normalized: normalized = tokens return " ".join(normalized).strip() def key_tokens(key: str): return [t for t in key.split() if t] def match_score_by_tokens(user_key: str, rep_key: str) -> float: if not user_key or not rep_key: return 0.0 u_toks = set(key_tokens(user_key)) r_toks = set(key_tokens(rep_key)) if not u_toks or not r_toks: return 0.0 inter = len(u_toks & r_toks) if inter == 0: return 0.0 containment = inter / min(len(u_toks), len(r_toks)) # подмножество токенов dice = (2 * inter) / (len(u_toks) + len(r_toks)) seq = difflib.SequenceMatcher(None, user_key, rep_key).ratio() return max(seq, dice, 0.98 * containment) def build_team_normalization_maps(raw_rows): key_to_counts = defaultdict(Counter) for league, date, home, away, o1, ox, o2 in raw_rows: kh = canonical_team_key(home) ka = canonical_team_key(away) if kh: key_to_counts[kh][home] += 1 if ka: key_to_counts[ka][away] += 1 rep_by_key = {} alias_to_rep = {} for key, cnt in key_to_counts.items(): most = cnt.most_common() max_count = most[0][1] candidates = [name for name, c in most if c == max_count] rep = min(candidates, key=lambda x: (len(x), x.lower())) rep_by_key[key] = rep for name in cnt.keys(): alias_to_rep[name] = rep rep_names = set(rep_by_key.values()) rep_key_by_name = {rep: canonical_team_key(rep) for rep in rep_names} return rep_by_key, alias_to_rep, rep_names, rep_key_by_name def resolve_user_team_name( user_name: str, alias_to_rep, rep_by_key, rep_names, rep_key_by_name, fuzzy_min_ratio=0.84, ambiguity_eps=0.02, margin=0.08 ): cleaned = clean_team_name(user_name) if cleaned in rep_names: return cleaned, None if cleaned in alias_to_rep: return alias_to_rep[cleaned], None key = canonical_team_key(cleaned) if key in rep_by_key: rep = rep_by_key[key] if rep != cleaned: return rep, f"Нормализация: '{cleaned}' -> '{rep}'" return rep, None scored = [] for rep in rep_names: rep_key = rep_key_by_name.get(rep, "") score = match_score_by_tokens(key, rep_key) if score > 0: scored.append((score, rep)) if not scored: return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." scored.sort(reverse=True, key=lambda x: x[0]) best_score, best_rep = scored[0] second_score = scored[1][0] if len(scored) > 1 else 0.0 near_best = [rep for sc, rep in scored if sc >= best_score - ambiguity_eps] if len(near_best) > 1 and best_score < 0.95: return cleaned, ( f"ВНИМАНИЕ: '{cleaned}' неоднозначно (ключ='{key}'), возможные варианты: " f"{', '.join(near_best[:6])}" + (" ..." if len(near_best) > 6 else "") ) if best_score >= fuzzy_min_ratio and (best_score >= 0.95 or (best_score - second_score) >= margin): return best_rep, f"Fuzzy/token-нормализация: '{cleaned}' -> '{best_rep}' (score={best_score:.2f})" return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." def split_pair_robust(p: str): p = normalize_dashes(p) if " - " in p: a, b = p.split(" - ", 1) return a.strip(), b.strip() parts = re.split(r"\s+[-]\s+", p) if len(parts) == 2: return parts[0].strip(), parts[1].strip() parts2 = re.split(r"\s*-\s*", p) if len(parts2) == 2: return parts2[0].strip(), parts2[1].strip() return None # ===== signatures (чтобы не плодить дубликаты цепочек) ===== def line_compact(s: str) -> str: s = normalize_dashes(str(s)) s = re.sub(r"\s+", " ", s).strip() return s def signature_from_chain_base_lines(base_lines): # base_lines = ["date | home-away", ...] return "\n".join(line_compact(x) for x in base_lines) # ✅ NEW: safe conversion for RichText -> str (для высоты строк и сигнатур) def _plain_text(value) -> str: if value is None: return "" if isinstance(value, CellRichText): return "".join(tb.text for tb in value) return str(value) def signature_from_matches_cell(text): if not text: return "" text = _plain_text(text) lines = [] for ln in str(text).splitlines(): ln = normalize_dashes(ln).strip() # ✅ убираем "(odds)" в конце строки (чтобы сигнатура совпадала даже при обновлении odds) ln = re.sub(r"\s*$[^)]*$\s*$", "", ln).strip() ln = re.sub(r"\s+", " ", ln).strip() if ln: lines.append(ln) return "\n".join(lines) # ===================== RichText coloring for teams ===================== # Настрой цвета/стиля тут: INLINE_MONO = InlineFont(rFont="Consolas") # обычный текст INLINE_HOME_HL = InlineFont(rFont="Consolas", b=True, color="1F4E79") # стартовая команда (HOME) — тёмно-синий INLINE_AWAY_HL = InlineFont(rFont="Consolas", b=True, color="9C0006") # конечная команда (AWAY) — тёмно-красный def build_matches_rich_text(chain, start_team, end_team): """ Возвращает CellRichText для колонки 'Matches', где: - start_team подсвечивается, если он стоит ДОМА (home) в строке - end_team подсвечивается, если он стоит В ГОСТЯХ (away) в строке """ base_lines = [f"{m[1]} | {m[2]}-{m[3]}" for m in chain] max_base_len = max((len(b) for b in base_lines), default=0) blocks = [] for idx, match in enumerate(chain): _league, date, home, away, o1, ox, o2 = match base = f"{date} | {home}-{away}" pad_spaces = " " * (max_base_len - len(base) + 2) odds_str = f"({fmt2(o1)}, {fmt2(ox)}, {fmt2(o2)})" blocks.append(TextBlock(INLINE_MONO, f"{date} | ")) blocks.append(TextBlock(INLINE_HOME_HL if home == start_team else INLINE_MONO, str(home))) blocks.append(TextBlock(INLINE_MONO, "-")) blocks.append(TextBlock(INLINE_AWAY_HL if away == end_team else INLINE_MONO, str(away))) blocks.append(TextBlock(INLINE_MONO, f"{pad_spaces}{odds_str}")) if idx != len(chain) - 1: blocks.append(TextBlock(INLINE_MONO, "\n")) return CellRichText(blocks) # ===================== read matches ===================== df = pd.read_excel(excel_file_path) raw_rows = [] for _, row in df.iterrows(): league = row[0] date = row[1] home = clean_team_name(row[2]) away = clean_team_name(row[3]) odds1 = row[4] odds_draw = row[5] odds2 = row[6] raw_rows.append((league, date, home, away, odds1, odds_draw, odds2)) rep_by_key, alias_to_rep, rep_names, rep_key_by_name = build_team_normalization_maps(raw_rows) matches = [] for league, date, home, away, odds1, odds_draw, odds2 in raw_rows: home_rep = alias_to_rep.get(home, home) away_rep = alias_to_rep.get(away, away) matches.append((league, date, home_rep, away_rep, odds1, odds_draw, odds2)) # ===================== chains ===================== def find_chains(matches, start_team, end_team, min_depth=1, max_depth=3): graph = {} for match in matches: league, date, home_team, away_team, odds1, odds_draw, odds2 = match graph.setdefault(home_team, []) graph.setdefault(away_team, []) graph[home_team].append((away_team, match)) graph[away_team].append((home_team, match)) chains = [] queue = deque([(start_team, [], set())]) while queue: current_team, path, visited = queue.popleft() if current_team == end_team and path: if min_depth <= len(path) <= max_depth: chains.append(path) continue if len(path) >= max_depth: continue for neighbor, match in graph.get(current_team, []): if match not in visited: new_visited = visited.copy() new_visited.add(match) queue.append((neighbor, path + [match], new_visited)) return chains # ===================== input pairs ===================== raw_input_teams = input( "Введите либо 2 команды (как раньше), либо список пар через запятую.\n" "Пример: Malaga - Granada, Granada - Albacete\n" "Можно использовать '-', '–' или '—'.\n" "Ввод: " ).strip() raw_input_teams = sanitize_pair_text(raw_input_teams) team_pairs = [] has_any_dash = '-' in raw_input_teams if (',' in raw_input_teams) or has_any_dash: parts = [p.strip() for p in re.split(r"[,\n;]+", raw_input_teams) if p.strip()] for p in parts: p = sanitize_pair_text(p) if not p: continue sp = split_pair_robust(p) if not sp: print(f"Пропуск (неверный формат пары, нужен 'Команда1 - Команда2'): {p}") continue a, b = sp a = clean_team_name(a) b = clean_team_name(b) if a and b: team_pairs.append((a, b)) if not team_pairs: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] else: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] resolved_pairs = [] for a, b in team_pairs: ra, wa = resolve_user_team_name(a, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) rb, wb = resolve_user_team_name(b, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) if wa: print(wa) if wb: print(wb) resolved_pairs.append((ra, rb)) team_pairs = resolved_pairs # ===================== calculator ===================== class TeamStrengthCalculator: def __init__(self): self.games = [] self.equations_method_2 = [] self.teams = set() def add_games(self, games): for g in games: league, date, home_team, away_team, home_odds, draw_odds, away_odds = g self.games.append({ 'league': league, 'date': date, 'home_team': clean_team_name(home_team), 'away_team': clean_team_name(away_team), 'home_odds': to_float(home_odds), 'draw_odds': to_float(draw_odds), 'away_odds': to_float(away_odds) }) self.teams.add(clean_team_name(home_team)) self.teams.add(clean_team_name(away_team)) def calculate_strength_difference_method_2(self): for game in self.games: league_name = game['league'] home_team = game['home_team'] away_team = game['away_team'] home_odds = game['home_odds'] away_odds = game['away_odds'] threshold_home, threshold_away = league_thresholds.get(league_name, (2.40, 3.00)) if home_odds < away_odds: if home_odds < threshold_home: home_strength = abs((100 / threshold_home) - (100 / home_odds)) self.equations_method_2.append( f"{home_team} = {away_team} + {home_strength:.3f}" ) else: home_strength = abs((100 / home_odds) - (100 / threshold_home)) self.equations_method_2.append( f"{away_team} = {home_team} + {home_strength:.3f}" ) else: if away_odds < threshold_away: away_strength = abs((100 / threshold_away) - (100 / away_odds)) self.equations_method_2.append( f"{away_team} = {home_team} + {away_strength:.3f}" ) else: away_strength = abs((100 / away_odds) - (100 / threshold_away)) self.equations_method_2.append( f"{home_team} = {away_team} + {away_strength:.3f}" ) def _safe_sympy_symbol(self, team: str): base = canonical_team_key(team).replace(" ", "_") base = re.sub(r"[^0-9a-zA-Z_]", "_", base) if not base: base = "team" if base[0].isdigit(): base = "t_" + base return symbols(base) def simplify_with_sympy_method2(self, start_team, end_team): if not self.games: return "", ["Нет матчей для расчета."], ("", "") first_league = self.games[0]['league'] threshold_home, threshold_away = league_thresholds.get(first_league, (2.40, 3.00)) team_symbols = {} for team in self.teams: if team == start_team: team_symbols[team] = 0 else: team_symbols[team] = self._safe_sympy_symbol(team) sympy_equations = [] for equation in self.equations_method_2: parts = equation.split('=') if len(parts) == 2 and '+' in parts[1]: left_team, right = parts[0].strip(), parts[1].strip() right_team, strength_diff = right.split('+') right_team = right_team.strip() strength_diff = float(strength_diff.strip()) left_sym = team_symbols[left_team] right_sym = team_symbols[right_team] sympy_equations.append(Eq(left_sym, right_sym + strength_diff)) symbols_list = [sym for sym in team_symbols.values() if sym != 0] solution = solve(sympy_equations, symbols_list, dict=True) if sympy_equations else [] end_symbol = team_symbols.get(end_team) if not solution or end_symbol is None: return "", ["Нет решения для метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") sol = solution[0] if end_symbol not in sol: return "", [f"Команда {end_team} не найдена в решении метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") try: end_value_numeric = float(sol[end_symbol].evalf()) except Exception: return "", [f"Не удалось вычислить численное значение силы {end_team} в методе 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") strength_diff = -end_value_numeric new_odds_start = 100 / ((100 / threshold_home) + strength_diff) new_odds_end = 100 / ((100 / threshold_home) - strength_diff) method2_str = ( f"{start_team} = {end_team} + {strength_diff:.3f}; " f"{start_team} odds = {new_odds_start:.3f}; {end_team} odds = {new_odds_end:.3f}" ) return method2_str, [], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") # ===================== Excel styles ===================== thin = Side(style="thin", color="000000") medium = Side(style="medium", color="000000") BORDER_THIN = Border(left=thin, right=thin, top=thin, bottom=thin) BORDER_MEDIUM_TOP = Border(left=thin, right=thin, top=medium, bottom=thin) ALIGN_WRAP_TOP = Alignment(wrap_text=True, vertical="top") ALIGN_CENTER = Alignment(horizontal="center", vertical="center", wrap_text=True) FONT_HEADER = Font(bold=True, size=11) FONT_BOLD = Font(bold=True) FONT_MONO = Font(name="Consolas") FILL_HEADER = PatternFill("solid", fgColor="D9E1F2") FILL_PAIR = PatternFill("solid", fgColor="E2EFDA") FILL_NEW_CHAIN = PatternFill("solid", fgColor="FFF2CC") # жёлтый FILL_NONE = PatternFill() # без заливки EXPECTED_HEADERS = [ "RUN", "Request #", "Start", "End", "Th home", "Th away", "Avg Date", "Matches (Date | Home-Away (1,X,2))", "Result" ] def init_results_workbook(output_excel_path): if os.path.exists(output_excel_path): wb = load_workbook(output_excel_path) else: wb = Workbook() if "Results" in wb.sheetnames: ws = wb["Results"] else: ws = wb.active ws.title = "Results" if ws.max_row == 1 and ws["A1"].value is None: ws.append(EXPECTED_HEADERS) else: current = [ws.cell(row=1, column=i).value for i in range(1, len(EXPECTED_HEADERS) + 1)] if current != EXPECTED_HEADERS: base = "Results_v2" name = base i = 2 while name in wb.sheetnames: name = f"{base}_{i}" i += 1 ws = wb.create_sheet(name) ws.append(EXPECTED_HEADERS) for col in range(1, len(EXPECTED_HEADERS) + 1): c = ws.cell(row=1, column=col) c.font = FONT_HEADER c.fill = FILL_HEADER c.alignment = ALIGN_CENTER c.border = BORDER_THIN widths = [18, 9, 18, 18, 9, 9, 11, 70, 55] for i, w in enumerate(widths, start=1): ws.column_dimensions[get_column_letter(i)].width = w ws.freeze_panes = "A2" return wb, ws def apply_row_style(ws, r, is_pair_first_row: bool, is_new_chain: bool): for col in range(1, len(EXPECTED_HEADERS) + 1): cell = ws.cell(row=r, column=col) cell.alignment = ALIGN_WRAP_TOP cell.border = BORDER_MEDIUM_TOP if is_pair_first_row else BORDER_THIN # Сначала чистим заливку, потом накладываем нужную cell.fill = FILL_NONE # Подсветка новых цепочек — приоритетнее if is_new_chain: cell.fill = FILL_NEW_CHAIN else: # Подсветка пары (как было) только на первой строке блока и только B,C,D if is_pair_first_row and col in (2, 3, 4): cell.fill = FILL_PAIR # Fonts if is_pair_first_row and col in (2, 3, 4): cell.font = FONT_BOLD elif col == 8: cell.font = FONT_MONO else: cell.font = Font() # default def set_row_height_from_matches(ws, r, matches_text): matches_text = _plain_text(matches_text) line_count = matches_text.count("\n") + 1 if matches_text else 1 ws.row_dimensions[r].height = min(max(18, 14 * line_count), 260) def append_row(ws, row_values, is_new_pair=False, is_new_chain=False): ws.append(row_values) r = ws.max_row apply_row_style(ws, r, is_new_pair, is_new_chain) set_row_height_from_matches(ws, r, row_values[7]) def find_last_segment_for_pair(ws, start_team: str, end_team: str): """ Ищем последний (самый нижний) непрерывный блок строк, где Start/End совпадают. Возвращает (seg_start, seg_end) или None. """ start_col = 3 # C end_col = 4 # D segments = [] in_seg = False seg_start = None for r in range(2, ws.max_row + 1): s = ws.cell(row=r, column=start_col).value e = ws.cell(row=r, column=end_col).value s = clean_team_name(s) if s else "" e = clean_team_name(e) if e else "" if s == start_team and e == end_team: if not in_seg: in_seg = True seg_start = r else: if in_seg: segments.append((seg_start, r - 1)) in_seg = False seg_start = None if in_seg: segments.append((seg_start, ws.max_row)) if not segments: return None return segments[-1] # ===================== MAIN ===================== run_dt = datetime.now() run_stamp = run_dt.strftime("%d.%m.%Y %H:%M:%S") out_dir = os.path.dirname(excel_file_path) if os.path.dirname(excel_file_path) else os.getcwd() output_excel_path = os.path.join(out_dir, "wtp_results.xlsx") wb, ws = init_results_workbook(output_excel_path) for request_num, (start_team, end_team) in enumerate(team_pairs, start=1): chains = find_chains(matches, start_team, end_team) # убрать дубликаты цепочек (по матчам) unique_chains = [] seen = set() for ch in chains: t = tuple(ch) if t not in seen: seen.add(t) unique_chains.append(ch) chains = unique_chains # ---- формируем desired_rows: список строк, которые должны быть в Excel для этой пары ---- desired_rows = [] if not chains: desired_rows.append({ "signature": "", "values": [run_stamp, request_num, start_team, end_team, "", "", "", "", ""] }) else: # группировка по длине, сортировка по средней дате (свежие сверху) groups = {} for chain in chains: L = len(chain) groups.setdefault(L, []) dts = [parse_date_to_dt(m[1]) for m in chain] dts = [d for d in dts if d] avg_date = datetime.fromtimestamp(sum(d.timestamp() for d in dts) / len(dts)) if dts else datetime.min groups[L].append({"chain": chain, "avg_date": avg_date}) for L in groups: groups[L] = sorted(groups[L], key=lambda x: x["avg_date"], reverse=True) for L in sorted(groups.keys()): for info in groups[L]: chain = info["chain"] avg_date = info["avg_date"] avg_date_str = avg_date.strftime("%d.%m.%Y") if avg_date != datetime.min else "" games = [] base_lines = [] used_league_for_threshold = None for match in chain: league, date, home, away, o1, ox, o2 = match games.append(match) if used_league_for_threshold is None: used_league_for_threshold = league base_lines.append(f"{date} | {home}-{away}") # signature без odds (чтобы совпадало даже если odds обновились) chain_sig = signature_from_chain_base_lines(base_lines) # ✅ RichText (подсветка start_team как HOME и end_team как AWAY) matches_cell_value = build_matches_rich_text(chain, start_team, end_team) th_home, th_away = league_thresholds.get(used_league_for_threshold, (2.40, 3.00)) th_home_str = f"{th_home:.2f}" th_away_str = f"{th_away:.2f}" calc = TeamStrengthCalculator() calc.add_games(games) calc.calculate_strength_difference_method_2() result2, warnings, _ths = calc.simplify_with_sympy_method2(start_team, end_team) desired_rows.append({ "signature": chain_sig, "values": [ run_stamp, # RUN request_num, # Request # start_team, # Start end_team, # End th_home_str, # Th home th_away_str, # Th away avg_date_str, # Avg Date matches_cell_value, # Matches (RichText) result2 # Result ] }) # ---- обновляем существующий блок для пары (или добавляем новый) ---- seg = find_last_segment_for_pair(ws, start_team, end_team) if seg is None: # пары ещё нет в файле — просто добавляем блок (без жёлтого) first = True for item in desired_rows: append_row(ws, item["values"], is_new_pair=first, is_new_chain=False) first = False continue seg_start, seg_end = seg current_len = seg_end - seg_start + 1 desired_len = len(desired_rows) # существующие signatures (по текущему блоку) existing_sigs = set() for r in range(seg_start, seg_end + 1): sig = signature_from_matches_cell(ws.cell(row=r, column=8).value) # H existing_sigs.add(sig) # подгоняем размер блока под desired_len if desired_len > current_len: insert_at = seg_end + 1 ws.insert_rows(insert_at, amount=(desired_len - current_len)) seg_end += (desired_len - current_len) elif desired_len < current_len: delete_from = seg_start + desired_len ws.delete_rows(delete_from, amount=(current_len - desired_len)) seg_end = seg_start + desired_len - 1 # перезаписываем строки блока for i, item in enumerate(desired_rows): r = seg_start + i vals = item["values"] sig = item["signature"] is_pair_first_row = (i == 0) # новая цепочка — если ее сигнатуры не было раньше (и сигнатура не пустая) is_new_chain = (sig != "" and sig not in existing_sigs) # записываем значения for col_idx, v in enumerate(vals, start=1): ws.cell(row=r, column=col_idx, value=v) # применяем стили apply_row_style(ws, r, is_pair_first_row, is_new_chain) set_row_height_from_matches(ws, r, vals[7]) wb.save(output_excel_path) print(f"\nГотово. Результаты обновлены в Excel:\n{output_excel_path}")
Если хочешь другой сценарий подсветки (например: подсвечивать start-team везде, где он встречается (и дома и в гостях) или подсвечивать обе команды в любой позиции), скажи — это меняется буквально в 2 сравнениях внутри build_matches_rich_text().
22.12.2025 - 05:00 | Cadiz-Castellon (4.06, 3.51, 1.99)10.01.2026 - 04:30 | Cadiz-Gijon (2.85, 3.12, 2.77)21.12.2025 - 02:30 | Leganes-Gijon (2.52, 2.96, 3.35) подсветка сработала все хорошо, но вот цепочки теперь просто в строчку, они должны быть в столбик как раншье, вот так вот:
22.12.2025 - 00:15 | Mirandes-Cordoba (3.24, 3.26, 2.39)
04.01.2026 - 05:00 | Cordoba-Burgos CF (2.00, 3.17, 4.55)
15.12.2025 - 02:30 | Almeria-Burgos CF (1.78, 3.56, 5.20) переделай и вышли мне полный код
Понял: подсветка работает, но переносы строк внутри RichText Excel не отрисовал, поэтому всё “слиплось” в одну строку. Это бывает, когда \n идёт отдельным TextBlock’ом. Надёжнее — добавлять \n в конец последнего фрагмента строки (обычно туда, где odds), а не отдельным блоком.
Ниже полный код с исправлением: в build_matches_rich_text() перенос строки добавляется в тот же TextBlock, где заканчивается строка.
pythonimport os import re import unicodedata import difflib import pandas as pd from collections import deque, defaultdict, Counter from sympy import symbols, Eq, solve from datetime import datetime, timedelta from openpyxl import Workbook, load_workbook from openpyxl.styles import Alignment, Font, PatternFill, Border, Side from openpyxl.utils import get_column_letter # ✅ Rich text support (font colors inside a single cell) from openpyxl.cell.rich_text import CellRichText, TextBlock from openpyxl.cell.text import InlineFont # ===================== НАСТРОЙКИ ===================== excel_file_path = r"C:\Users\User\Desktop\results\results.xlsx" # ===================================================== league_thresholds = { "Albania Superiore": (2.52, 2.73), "Andorra Primera": (2.42, 2.75), "Armenia Premier": (2.32, 3.20), "Bosnia WWin Liga": (2.00, 3.20), "Croatia HNL": (2.29, 3.25), "Cyprus League": (2.25, 3.20), "Cyprus Division 2": (2.46, 2.70), "Czech Chance Liga": (2.25, 3.30), "Denmark Superliga": (2.40, 3.00), "Greece Super League": (2.36, 3.40), "Greece Super League 2": (2.25, 3.30), "Hungary OTP Bank Liga": (2.17, 3.40), "Hungary Merkantil Bank Liga": (2.38, 3.30), "Luxembourg BGL Ligue": (2.20, 3.00), "Malta Premier League": (2.75, 2.60), "Montenegro Prva Liga": (2.50, 3.20), "North Macedonia 1 MFL": (2.13, 3.60), "Slovakia Nike Liga": (2.30, 3.00), "Slovenia Prva Liga": (2.47, 3.00), "Algeria Ligue 2": (1.87, 5.00), "Mexico Liga de Expansion MX": (2.00, 4.00), "South Africa Premiership": (2.31, 3.45), "Croatia Prva NL": (2.40, 2.80), "India ISL": (2.17, 3.33), "Indonesia Liga 1": (2.27, 3.45), "Bulgaria Vtora liga": (2.27, 3.45), "Zambia Super League": (2.47, 3.10), "Romania Liga 3": (2.30, 2.94), "Myanmar National League": (2.50, 2.50), "Tanzania Ligi Kuu Bara": (2.20, 3.30), "France Nacional": (2.32, 3.30), "Nigeria NPFL": (1.50, 6.00), "Turkey 1.Lig": (2.27, 3.20), "Algeria Ligue 1": (2.05, 4.30), "Italy Serie C - A": (2.38, 3.30), "Italy Serie B": (2.46, 3.50), "Algeria Ligue 2 - 21": (2.00, 3.20), "England National League South": (2.38, 3.00), "Brazil Paulista A4": (2.44, 3.00), "Ethiopia": (3.12, 2.85), "Spain LaLiga": (2.29, 3.61), "Australia NPL": (2.22, 3.00), "Bulgaria Vtora Liga": (2.08, 3.70), "Italy Serie C - C": (2.40, 3.20), "Spain Segunda": (2.11, 4.02), "France Ligue 1": (2.30, 3.60), "Brazil Serie A": (2.05, 4.00), "Brazil Serie B": (2.05, 4.00), "Brazil Serie C": (2.15, 3.70), "Iceland Besta Delid": (2.12, 3.10), "Australia NPL Northern": (2.47, 2.30), "Norway Division 2": (2.08, 2.94), "USA MLS": (2.27, 3.20), "Argentina": (2.22, 3.80), "Mexico": (2.08, 3.80), "Bundesliga - 2": (2.16, 3.55), "France - 2": (2.16, 3.55), "Netherlands - Eridivisie": (2.20, 3.20), "England - Premier League": (2.18, 3.60) } # ===================== helpers ===================== def normalize_dashes(text): if isinstance(text, str): return text.replace('–', '-').replace('—', '-').replace('−', '-') return text def clean_team_name(name): if isinstance(name, str): name = normalize_dashes(name) return ' '.join(name.strip().split()) return name def sanitize_pair_text(p): if not isinstance(p, str): return p p = p.strip() p = normalize_dashes(p) p = re.sub(r"\s*->\s*&\s*[A-Za-z]:[\\/].*$", "", p) p = re.sub(r"\s*&\s*[A-Za-z]:[\\/].*$", "", p) return p.strip() def parse_date_to_dt(raw_date): if isinstance(raw_date, datetime): return raw_date if isinstance(raw_date, (float, int)): try: return datetime(1899, 12, 30) + timedelta(days=int(raw_date)) except: return None if isinstance(raw_date, str): try: if ' - ' in raw_date: date_part = raw_date.split(' - ')[0].strip() return datetime.strptime(date_part, '%d.%m.%Y') return datetime.strptime(raw_date.strip(), '%d.%m.%Y') except: return None return None def to_float(x): return float(str(x).replace(',', '.')) def fmt2(x) -> str: try: return f"{to_float(x):.2f}" except: return str(x) def strip_accents(s: str) -> str: s = unicodedata.normalize("NFKD", s) return "".join(ch for ch in s if not unicodedata.combining(ch)) ORG_TOKENS = { "fc","cf","ad","cd","ud","sc","ac","afc","fk","sk","nk","as","ss","sv","if","bk","kf", "cfc","fcd","f.c","c.f","a.d","u.d","c.d","s.c","a.c", "club","clube","clubs","football","futbol","fútbol","calcio" } CONNECTOR_TOKENS = { "de","del","la","las","los","el","da","do","di","du","der","den","van","von","the","of","and" } ABBREV_MAP = { "dep": "deportivo", "depor": "deportivo", } def canonical_team_key(name: str) -> str: if not isinstance(name, str): return "" s = clean_team_name(name) s = strip_accents(s.lower()) s = re.sub(r"[^0-9a-z\s]", " ", s) tokens = [t for t in s.split() if t] normalized = [] for t in tokens: t = ABBREV_MAP.get(t, t) if t in ORG_TOKENS: continue if t in CONNECTOR_TOKENS: continue normalized.append(t) if not normalized: normalized = tokens return " ".join(normalized).strip() def key_tokens(key: str): return [t for t in key.split() if t] def match_score_by_tokens(user_key: str, rep_key: str) -> float: if not user_key or not rep_key: return 0.0 u_toks = set(key_tokens(user_key)) r_toks = set(key_tokens(rep_key)) if not u_toks or not r_toks: return 0.0 inter = len(u_toks & r_toks) if inter == 0: return 0.0 containment = inter / min(len(u_toks), len(r_toks)) dice = (2 * inter) / (len(u_toks) + len(r_toks)) seq = difflib.SequenceMatcher(None, user_key, rep_key).ratio() return max(seq, dice, 0.98 * containment) def build_team_normalization_maps(raw_rows): key_to_counts = defaultdict(Counter) for league, date, home, away, o1, ox, o2 in raw_rows: kh = canonical_team_key(home) ka = canonical_team_key(away) if kh: key_to_counts[kh][home] += 1 if ka: key_to_counts[ka][away] += 1 rep_by_key = {} alias_to_rep = {} for key, cnt in key_to_counts.items(): most = cnt.most_common() max_count = most[0][1] candidates = [name for name, c in most if c == max_count] rep = min(candidates, key=lambda x: (len(x), x.lower())) rep_by_key[key] = rep for name in cnt.keys(): alias_to_rep[name] = rep rep_names = set(rep_by_key.values()) rep_key_by_name = {rep: canonical_team_key(rep) for rep in rep_names} return rep_by_key, alias_to_rep, rep_names, rep_key_by_name def resolve_user_team_name( user_name: str, alias_to_rep, rep_by_key, rep_names, rep_key_by_name, fuzzy_min_ratio=0.84, ambiguity_eps=0.02, margin=0.08 ): cleaned = clean_team_name(user_name) if cleaned in rep_names: return cleaned, None if cleaned in alias_to_rep: return alias_to_rep[cleaned], None key = canonical_team_key(cleaned) if key in rep_by_key: rep = rep_by_key[key] if rep != cleaned: return rep, f"Нормализация: '{cleaned}' -> '{rep}'" return rep, None scored = [] for rep in rep_names: rep_key = rep_key_by_name.get(rep, "") score = match_score_by_tokens(key, rep_key) if score > 0: scored.append((score, rep)) if not scored: return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." scored.sort(reverse=True, key=lambda x: x[0]) best_score, best_rep = scored[0] second_score = scored[1][0] if len(scored) > 1 else 0.0 near_best = [rep for sc, rep in scored if sc >= best_score - ambiguity_eps] if len(near_best) > 1 and best_score < 0.95: return cleaned, ( f"ВНИМАНИЕ: '{cleaned}' неоднозначно (ключ='{key}'), возможные варианты: " f"{', '.join(near_best[:6])}" + (" ..." if len(near_best) > 6 else "") ) if best_score >= fuzzy_min_ratio and (best_score >= 0.95 or (best_score - second_score) >= margin): return best_rep, f"Fuzzy/token-нормализация: '{cleaned}' -> '{best_rep}' (score={best_score:.2f})" return cleaned, f"ВНИМАНИЕ: команда '{cleaned}' не найдена для нормализации (ключ='{key}')." def split_pair_robust(p: str): p = normalize_dashes(p) if " - " in p: a, b = p.split(" - ", 1) return a.strip(), b.strip() parts = re.split(r"\s+[-]\s+", p) if len(parts) == 2: return parts[0].strip(), parts[1].strip() parts2 = re.split(r"\s*-\s*", p) if len(parts2) == 2: return parts2[0].strip(), parts2[1].strip() return None # ===== signatures ===== def line_compact(s: str) -> str: s = normalize_dashes(str(s)) s = re.sub(r"\s+", " ", s).strip() return s def signature_from_chain_base_lines(base_lines): return "\n".join(line_compact(x) for x in base_lines) def _plain_text(value) -> str: if value is None: return "" if isinstance(value, CellRichText): return "".join(tb.text for tb in value) return str(value) def signature_from_matches_cell(text): if not text: return "" text = _plain_text(text) lines = [] for ln in str(text).splitlines(): ln = normalize_dashes(ln).strip() ln = re.sub(r"\s*$[^)]*$\s*$", "", ln).strip() ln = re.sub(r"\s+", " ", ln).strip() if ln: lines.append(ln) return "\n".join(lines) # ===================== RichText coloring ===================== INLINE_MONO = InlineFont(rFont="Consolas") INLINE_HOME_HL = InlineFont(rFont="Consolas", b=True, color="1F4E79") # start-team as HOME INLINE_AWAY_HL = InlineFont(rFont="Consolas", b=True, color="9C0006") # end-team as AWAY def build_matches_rich_text(chain, start_team, end_team): """ CellRichText для колонки Matches. Важно: переносы строк добавляем В КОНЕЦ последнего TextBlock строки, чтобы Excel корректно показывал "в столбик". """ base_lines = [f"{m[1]} | {m[2]}-{m[3]}" for m in chain] max_base_len = max((len(b) for b in base_lines), default=0) blocks = [] for idx, match in enumerate(chain): _league, date, home, away, o1, ox, o2 = match base = f"{date} | {home}-{away}" pad_spaces = " " * (max_base_len - len(base) + 2) odds_str = f"({fmt2(o1)}, {fmt2(ox)}, {fmt2(o2)})" blocks.append(TextBlock(INLINE_MONO, f"{date} | ")) blocks.append(TextBlock(INLINE_HOME_HL if home == start_team else INLINE_MONO, str(home))) blocks.append(TextBlock(INLINE_MONO, "-")) blocks.append(TextBlock(INLINE_AWAY_HL if away == end_team else INLINE_MONO, str(away))) # ✅ перенос строки добавляем сюда же (а не отдельным блоком) tail = f"{pad_spaces}{odds_str}" if idx != len(chain) - 1: tail += "\n" blocks.append(TextBlock(INLINE_MONO, tail)) return CellRichText(blocks) # ===================== read matches ===================== df = pd.read_excel(excel_file_path) raw_rows = [] for _, row in df.iterrows(): league = row[0] date = row[1] home = clean_team_name(row[2]) away = clean_team_name(row[3]) odds1 = row[4] odds_draw = row[5] odds2 = row[6] raw_rows.append((league, date, home, away, odds1, odds_draw, odds2)) rep_by_key, alias_to_rep, rep_names, rep_key_by_name = build_team_normalization_maps(raw_rows) matches = [] for league, date, home, away, odds1, odds_draw, odds2 in raw_rows: home_rep = alias_to_rep.get(home, home) away_rep = alias_to_rep.get(away, away) matches.append((league, date, home_rep, away_rep, odds1, odds_draw, odds2)) # ===================== chains ===================== def find_chains(matches, start_team, end_team, min_depth=1, max_depth=3): graph = {} for match in matches: league, date, home_team, away_team, odds1, odds_draw, odds2 = match graph.setdefault(home_team, []) graph.setdefault(away_team, []) graph[home_team].append((away_team, match)) graph[away_team].append((home_team, match)) chains = [] queue = deque([(start_team, [], set())]) while queue: current_team, path, visited = queue.popleft() if current_team == end_team and path: if min_depth <= len(path) <= max_depth: chains.append(path) continue if len(path) >= max_depth: continue for neighbor, match in graph.get(current_team, []): if match not in visited: new_visited = visited.copy() new_visited.add(match) queue.append((neighbor, path + [match], new_visited)) return chains # ===================== input pairs ===================== raw_input_teams = input( "Введите либо 2 команды (как раньше), либо список пар через запятую.\n" "Пример: Malaga - Granada, Granada - Albacete\n" "Можно использовать '-', '–' или '—'.\n" "Ввод: " ).strip() raw_input_teams = sanitize_pair_text(raw_input_teams) team_pairs = [] has_any_dash = '-' in raw_input_teams if (',' in raw_input_teams) or has_any_dash: parts = [p.strip() for p in re.split(r"[,\n;]+", raw_input_teams) if p.strip()] for p in parts: p = sanitize_pair_text(p) if not p: continue sp = split_pair_robust(p) if not sp: print(f"Пропуск (неверный формат пары, нужен 'Команда1 - Команда2'): {p}") continue a, b = sp a = clean_team_name(a) b = clean_team_name(b) if a and b: team_pairs.append((a, b)) if not team_pairs: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] else: start_team = clean_team_name(raw_input_teams) end_team = clean_team_name(input("Введите название команды назначения: ").strip()) team_pairs = [(start_team, end_team)] resolved_pairs = [] for a, b in team_pairs: ra, wa = resolve_user_team_name(a, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) rb, wb = resolve_user_team_name(b, alias_to_rep, rep_by_key, rep_names, rep_key_by_name) if wa: print(wa) if wb: print(wb) resolved_pairs.append((ra, rb)) team_pairs = resolved_pairs # ===================== calculator ===================== class TeamStrengthCalculator: def __init__(self): self.games = [] self.equations_method_2 = [] self.teams = set() def add_games(self, games): for g in games: league, date, home_team, away_team, home_odds, draw_odds, away_odds = g self.games.append({ 'league': league, 'date': date, 'home_team': clean_team_name(home_team), 'away_team': clean_team_name(away_team), 'home_odds': to_float(home_odds), 'draw_odds': to_float(draw_odds), 'away_odds': to_float(away_odds) }) self.teams.add(clean_team_name(home_team)) self.teams.add(clean_team_name(away_team)) def calculate_strength_difference_method_2(self): for game in self.games: league_name = game['league'] home_team = game['home_team'] away_team = game['away_team'] home_odds = game['home_odds'] away_odds = game['away_odds'] threshold_home, threshold_away = league_thresholds.get(league_name, (2.40, 3.00)) if home_odds < away_odds: if home_odds < threshold_home: home_strength = abs((100 / threshold_home) - (100 / home_odds)) self.equations_method_2.append( f"{home_team} = {away_team} + {home_strength:.3f}" ) else: home_strength = abs((100 / home_odds) - (100 / threshold_home)) self.equations_method_2.append( f"{away_team} = {home_team} + {home_strength:.3f}" ) else: if away_odds < threshold_away: away_strength = abs((100 / threshold_away) - (100 / away_odds)) self.equations_method_2.append( f"{away_team} = {home_team} + {away_strength:.3f}" ) else: away_strength = abs((100 / away_odds) - (100 / threshold_away)) self.equations_method_2.append( f"{home_team} = {away_team} + {away_strength:.3f}" ) def _safe_sympy_symbol(self, team: str): base = canonical_team_key(team).replace(" ", "_") base = re.sub(r"[^0-9a-zA-Z_]", "_", base) if not base: base = "team" if base[0].isdigit(): base = "t_" + base return symbols(base) def simplify_with_sympy_method2(self, start_team, end_team): if not self.games: return "", ["Нет матчей для расчета."], ("", "") first_league = self.games[0]['league'] threshold_home, threshold_away = league_thresholds.get(first_league, (2.40, 3.00)) team_symbols = {} for team in self.teams: if team == start_team: team_symbols[team] = 0 else: team_symbols[team] = self._safe_sympy_symbol(team) sympy_equations = [] for equation in self.equations_method_2: parts = equation.split('=') if len(parts) == 2 and '+' in parts[1]: left_team, right = parts[0].strip(), parts[1].strip() right_team, strength_diff = right.split('+') right_team = right_team.strip() strength_diff = float(strength_diff.strip()) left_sym = team_symbols[left_team] right_sym = team_symbols[right_team] sympy_equations.append(Eq(left_sym, right_sym + strength_diff)) symbols_list = [sym for sym in team_symbols.values() if sym != 0] solution = solve(sympy_equations, symbols_list, dict=True) if sympy_equations else [] end_symbol = team_symbols.get(end_team) if not solution or end_symbol is None: return "", ["Нет решения для метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") sol = solution[0] if end_symbol not in sol: return "", [f"Команда {end_team} не найдена в решении метода 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") try: end_value_numeric = float(sol[end_symbol].evalf()) except Exception: return "", [f"Не удалось вычислить численное значение силы {end_team} в методе 2."], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") strength_diff = -end_value_numeric new_odds_start = 100 / ((100 / threshold_home) + strength_diff) new_odds_end = 100 / ((100 / threshold_home) - strength_diff) method2_str = ( f"{start_team} = {end_team} + {strength_diff:.3f}; " f"{start_team} odds = {new_odds_start:.3f}; {end_team} odds = {new_odds_end:.3f}" ) return method2_str, [], (f"{threshold_home:.2f}", f"{threshold_away:.2f}") # ===================== Excel styles ===================== thin = Side(style="thin", color="000000") medium = Side(style="medium", color="000000") BORDER_THIN = Border(left=thin, right=thin, top=thin, bottom=thin) BORDER_MEDIUM_TOP = Border(left=thin, right=thin, top=medium, bottom=thin) ALIGN_WRAP_TOP = Alignment(wrap_text=True, vertical="top") ALIGN_CENTER = Alignment(horizontal="center", vertical="center", wrap_text=True) FONT_HEADER = Font(bold=True, size=11) FONT_BOLD = Font(bold=True) FONT_MONO = Font(name="Consolas") FILL_HEADER = PatternFill("solid", fgColor="D9E1F2") FILL_PAIR = PatternFill("solid", fgColor="E2EFDA") FILL_NEW_CHAIN = PatternFill("solid", fgColor="FFF2CC") FILL_NONE = PatternFill() EXPECTED_HEADERS = [ "RUN", "Request #", "Start", "End", "Th home", "Th away", "Avg Date", "Matches (Date | Home-Away (1,X,2))", "Result" ] def init_results_workbook(output_excel_path): if os.path.exists(output_excel_path): wb = load_workbook(output_excel_path) else: wb = Workbook() if "Results" in wb.sheetnames: ws = wb["Results"] else: ws = wb.active ws.title = "Results" if ws.max_row == 1 and ws["A1"].value is None: ws.append(EXPECTED_HEADERS) else: current = [ws.cell(row=1, column=i).value for i in range(1, len(EXPECTED_HEADERS) + 1)] if current != EXPECTED_HEADERS: base = "Results_v2" name = base i = 2 while name in wb.sheetnames: name = f"{base}_{i}" i += 1 ws = wb.create_sheet(name) ws.append(EXPECTED_HEADERS) for col in range(1, len(EXPECTED_HEADERS) + 1): c = ws.cell(row=1, column=col) c.font = FONT_HEADER c.fill = FILL_HEADER c.alignment = ALIGN_CENTER c.border = BORDER_THIN widths = [18, 9, 18, 18, 9, 9, 11, 70, 55] for i, w in enumerate(widths, start=1): ws.column_dimensions[get_column_letter(i)].width = w ws.freeze_panes = "A2" return wb, ws def apply_row_style(ws, r, is_pair_first_row: bool, is_new_chain: bool): for col in range(1, len(EXPECTED_HEADERS) + 1): cell = ws.cell(row=r, column=col) cell.alignment = ALIGN_WRAP_TOP cell.border = BORDER_MEDIUM_TOP if is_pair_first_row else BORDER_THIN cell.fill = FILL_NONE if is_new_chain: cell.fill = FILL_NEW_CHAIN else: if is_pair_first_row and col in (2, 3, 4): cell.fill = FILL_PAIR if is_pair_first_row and col in (2, 3, 4): cell.font = FONT_BOLD elif col == 8: cell.font = FONT_MONO else: cell.font = Font() def set_row_height_from_matches(ws, r, matches_text): matches_text = _plain_text(matches_text) line_count = matches_text.count("\n") + 1 if matches_text else 1 ws.row_dimensions[r].height = min(max(18, 14 * line_count), 260) def append_row(ws, row_values, is_new_pair=False, is_new_chain=False): ws.append(row_values) r = ws.max_row apply_row_style(ws, r, is_new_pair, is_new_chain) set_row_height_from_matches(ws, r, row_values[7]) def find_last_segment_for_pair(ws, start_team: str, end_team: str): start_col = 3 end_col = 4 segments = [] in_seg = False seg_start = None for r in range(2, ws.max_row + 1): s = ws.cell(row=r, column=start_col).value e = ws.cell(row=r, column=end_col).value s = clean_team_name(s) if s else "" e = clean_team_name(e) if e else "" if s == start_team and e == end_team: if not in_seg: in_seg = True seg_start = r else: if in_seg: segments.append((seg_start, r - 1)) in_seg = False seg_start = None if in_seg: segments.append((seg_start, ws.max_row)) if not segments: return None return segments[-1] # ===================== MAIN ===================== run_dt = datetime.now() run_stamp = run_dt.strftime("%d.%m.%Y %H:%M:%S") out_dir = os.path.dirname(excel_file_path) if os.path.dirname(excel_file_path) else os.getcwd() output_excel_path = os.path.join(out_dir, "wtp_results.xlsx") wb, ws = init_results_workbook(output_excel_path) for request_num, (start_team, end_team) in enumerate(team_pairs, start=1): chains = find_chains(matches, start_team, end_team) unique_chains = [] seen = set() for ch in chains: t = tuple(ch) if t not in seen: seen.add(t) unique_chains.append(ch) chains = unique_chains desired_rows = [] if not chains: desired_rows.append({ "signature": "", "values": [run_stamp, request_num, start_team, end_team, "", "", "", "", ""] }) else: groups = {} for chain in chains: L = len(chain) groups.setdefault(L, []) dts = [parse_date_to_dt(m[1]) for m in chain] dts = [d for d in dts if d] avg_date = datetime.fromtimestamp(sum(d.timestamp() for d in dts) / len(dts)) if dts else datetime.min groups[L].append({"chain": chain, "avg_date": avg_date}) for L in groups: groups[L] = sorted(groups[L], key=lambda x: x["avg_date"], reverse=True) for L in sorted(groups.keys()): for info in groups[L]: chain = info["chain"] avg_date = info["avg_date"] avg_date_str = avg_date.strftime("%d.%m.%Y") if avg_date != datetime.min else "" games = [] base_lines = [] used_league_for_threshold = None for match in chain: league, date, home, away, o1, ox, o2 = match games.append(match) if used_league_for_threshold is None: used_league_for_threshold = league base_lines.append(f"{date} | {home}-{away}") chain_sig = signature_from_chain_base_lines(base_lines) matches_cell_value = build_matches_rich_text(chain, start_team, end_team) th_home, th_away = league_thresholds.get(used_league_for_threshold, (2.40, 3.00)) th_home_str = f"{th_home:.2f}" th_away_str = f"{th_away:.2f}" calc = TeamStrengthCalculator() calc.add_games(games) calc.calculate_strength_difference_method_2() result2, warnings, _ths = calc.simplify_with_sympy_method2(start_team, end_team) desired_rows.append({ "signature": chain_sig, "values": [ run_stamp, request_num, start_team, end_team, th_home_str, th_away_str, avg_date_str, matches_cell_value, result2 ] }) seg = find_last_segment_for_pair(ws, start_team, end_team) if seg is None: first = True for item in desired_rows: append_row(ws, item["values"], is_new_pair=first, is_new_chain=False) first = False continue seg_start, seg_end = seg current_len = seg_end - seg_start + 1 desired_len = len(desired_rows) existing_sigs = set() for r in range(seg_start, seg_end + 1): sig = signature_from_matches_cell(ws.cell(row=r, column=8).value) existing_sigs.add(sig) if desired_len > current_len: insert_at = seg_end + 1 ws.insert_rows(insert_at, amount=(desired_len - current_len)) seg_end += (desired_len - current_len) elif desired_len < current_len: delete_from = seg_start + desired_len ws.delete_rows(delete_from, amount=(current_len - desired_len)) seg_end = seg_start + desired_len - 1 for i, item in enumerate(desired_rows): r = seg_start + i vals = item["values"] sig = item["signature"] is_pair_first_row = (i == 0) is_new_chain = (sig != "" and sig not in existing_sigs) for col_idx, v in enumerate(vals, start=1): ws.cell(row=r, column=col_idx, value=v) apply_row_style(ws, r, is_pair_first_row, is_new_chain) set_row_height_from_matches(ws, r, vals[7]) wb.save(output_excel_path) print(f"\nГотово. Результаты обновлены в Excel:\n{output_excel_path}")
Если после этого где-то всё равно “слипается”, скажи версию openpyxl (или просто кинь pip show openpyxl) — на некоторых версиях RichText ведёт себя чуть иначе, и я дам 100% совместимый вариант через “частичное форматирование” без RichText (но подсветка будет уже не внутри строки, а, например, отдельными колонками/стилями).