94 lines
3.4 KiB
Python
94 lines
3.4 KiB
Python
import json
|
|
import os
|
|
import pandas as pd
|
|
import numpy as np
|
|
from datetime import timedelta
|
|
|
|
# 1. 整合数据
|
|
# data_dirs = ['data_test_dir', 'data_test_dir1']
|
|
data_dirs = ['data_test_dir']
|
|
all_records = []
|
|
|
|
for d in data_dirs:
|
|
if not os.path.exists(d): continue
|
|
for f in os.listdir(d):
|
|
if f.endswith('.json') and f != 'stat_result.json':
|
|
with open(os.path.join(d, f), 'r') as file:
|
|
try:
|
|
all_records.extend(json.load(file))
|
|
except:
|
|
continue
|
|
|
|
df = pd.DataFrame(all_records)
|
|
df = df.drop_duplicates(subset=['id'], keep='last')
|
|
df['time'] = pd.to_datetime(df['time'])
|
|
print(f"Total unique records: {len(df)}")
|
|
|
|
|
|
# 2. 极速统计函数
|
|
def calculate_stats_fast(group):
|
|
if group.empty: return {}
|
|
stats = {}
|
|
stats['winner_prob'] = group['winner'].value_counts(normalize=True).to_dict()
|
|
stats['GD1_prob'] = (group['winner'] >= 12).map({True: '冠亚大', False: '冠亚小'}).value_counts(
|
|
normalize=True).to_dict()
|
|
stats['GD2_prob'] = group['GD2'].value_counts(normalize=True).to_dict()
|
|
|
|
res_df = pd.DataFrame(group['result'].tolist())
|
|
pos_probs = {}
|
|
pos_detail_probs = {}
|
|
for col in range(10):
|
|
col_data = res_df[col]
|
|
pos_probs[f'pos_{col}'] = col_data.value_counts(normalize=True).to_dict()
|
|
is_big = (col_data >= 6).map({True: '大', False: '小'})
|
|
is_odd = (col_data % 2 != 0).map({True: '单', False: '双'})
|
|
pos_detail_probs[f'pos_{col}'] = {
|
|
'big_small': is_big.value_counts(normalize=True).to_dict(),
|
|
'odd_even': is_odd.value_counts(normalize=True).to_dict()
|
|
}
|
|
stats['result_pos_prob'] = pos_probs
|
|
stats['result_pos_detail_prob'] = pos_detail_probs
|
|
|
|
glh_df = pd.DataFrame(group['GLH_result'].tolist())
|
|
glh_pos_probs = {}
|
|
for col in range(5):
|
|
glh_pos_probs[f'pos_{col}'] = glh_df[col].value_counts(normalize=True).to_dict()
|
|
stats['GLH_pos_prob'] = glh_pos_probs
|
|
return stats
|
|
|
|
|
|
# 3. 多维度聚合
|
|
df['hour_min'] = df['time'].dt.strftime('%H:%M:%S')
|
|
df['day_of_month'] = df['time'].dt.day
|
|
df['day_of_week'] = df['time'].dt.dayofweek
|
|
|
|
# 全量统计
|
|
print("Calculating full history stats...")
|
|
time_stats = df.groupby('hour_min').apply(calculate_stats_fast).to_dict()
|
|
date_stats = df.groupby('day_of_month').apply(calculate_stats_fast).to_dict()
|
|
week_stats = df.groupby('day_of_week').apply(calculate_stats_fast).to_dict()
|
|
|
|
# 最近 100 天统计
|
|
print("Calculating recent 100 days stats...")
|
|
first_date = df['time'].min()
|
|
last_date = df['time'].max()
|
|
# 总预测命中率大概在 0.3241
|
|
# start_date_last_0000_1d = last_date - timedelta(days=int(len(df["time"]) * 0.3241 / 276))
|
|
# 取前 x 天，多了这 x 天会影响概率分布 + 万份之一
|
|
start_date_last_0000_2d = last_date - timedelta(days=(0.0001 * len(df["time"]) / 276) + 1)
|
|
df_0000_2d = df[df['time'] >= start_date_last_0000_2d]
|
|
time_stats_0000_2d = df_0000_2d.groupby('hour_min').apply(calculate_stats_fast).to_dict()
|
|
|
|
# 4. 保存结果
|
|
output_data = {
|
|
'by_time': time_stats,
|
|
'by_time_recent_0000_2d': time_stats_0000_2d,
|
|
'by_date': date_stats,
|
|
'by_week': week_stats,
|
|
'last_updated': last_date.strftime('%Y-%m-%d %H:%M:%S')
|
|
}
|
|
|
|
with open('data_test_predict/aggregated_stats_v7.json', 'w') as f:
|
|
json.dump(output_data, f)
|
|
|
|
print(f"Stats V7 generated with 100-day window. Last data point: {last_date}") |