#!/usr/bin/env python
# coding: utf-8

# In[23]:


import pandas as pd
import numpy as np
from tqdm.notebook import tqdm
import matplotlib.pyplot as plt

get_ipython().run_line_magic('matplotlib', 'inline')


# In[24]:


from xgboost import XGBClassifier
from sklearn.metrics import brier_score_loss, roc_auc_score
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.calibration import CalibratedClassifierCV
from scikitplot.metrics import plot_calibration_curve


# In[25]:


import warnings
warnings.filterwarnings('ignore', category=pd.io.pytables.PerformanceWarning)


# In[26]:


import os
data_dir = os.getcwd() + '/data/wy_scout/'


# In[27]:


df_games = pd.read_hdf(data_dir + 'spadl.h5', 'games')
df_games.tail(10)


# In[28]:


dfs_features = []
for _, game in tqdm(df_games.iterrows(), total=len(df_games)):
    game_id = game['game_id']
    df_features = pd.read_hdf(data_dir + 'features.h5', key=f'game_{game_id}')
    df_features['game_id'] = game_id
    dfs_features.append(df_features)
df_features = pd.concat(dfs_features).reset_index(drop=True)
df_features.tail(10)


# In[29]:


dfs_labels = []
"""
for _, game in tqdm(df_games.iterrows(), total=len(df_games)):
    game_id = game['game_id']
    df_labels = pd.read_hdf()
"""