from google.colab import files
files.upload()  #probspace_convini.zip

!unzip probspace_convini.zip

import warnings
warnings.simplefilter('ignore')

import pandas as pd
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()

from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_pinball_loss
from lightgbm import LGBMRegressor

train = pd.read_csv('convini_train_data.csv', index_col=0)
test = pd.read_csv('convini_test_data.csv', index_col=0)

x_train, x_valid, y_train, y_valid = train_test_split(
    train[['highest', 'lowest', 'rain']], train['ice1'], test_size=0.3, random_state=0)

lgb = LGBMRegressor(
    objective='quantile',   # 分位点回帰
    alpha=0.1,  # tutorialのqに相当
    n_estimators=1000,
    max_depth=5,
    colsample_bytree=0.5,
    random_state=0)
lgb.fit(x_train, y_train, eval_set=(x_valid, y_valid), early_stopping_rounds=100, verbose=50)

quantiles = [0.01, 0.1, 0.5, 0.9, 0.99]
lgb_scores = []
oof = np.zeros(len(x_valid)*len(quantiles)).reshape(len(x_valid), len(quantiles))

for i, q in enumerate(quantiles):
    lgb = LGBMRegressor(
        objective='quantile',
        alpha=q,
        n_estimators=10000,
        max_depth=5,
        colsample_bytree=0.5,
        random_state=0)
    lgb.fit(x_train, y_train, eval_set=(x_valid, y_valid), early_stopping_rounds=100, verbose=False)
    lgb_scores.append(lgb.best_score_['valid_0']['quantile'])  # validationのbest_score
    oof[:,i] = lgb.predict(x_valid)

print(lgb_scores)

oof_df = pd.DataFrame(y_valid).reset_index(drop=True)
for i, q in enumerate(quantiles):
    oof_df['oof_'+str(q)] = oof[:,i]

oof_df.sample(n=5)

pinball_sklearn = [mean_pinball_loss(oof_df['ice1'], oof_df['oof_'+str(q)], alpha=q) for q in quantiles]
print(pinball_sklearn)

fig, ax = plt.subplots(2,3, sharex=True, sharey=True, figsize=(16, 9))
for i, c in enumerate(quantiles):
    axy, axx = divmod(i,3)
    sns.scatterplot(y=f"oof_{quantiles[i]}", x='ice1', data=oof_df, ax=ax[axy,axx])
    ax[axy, axx].set_title(f"oof_{quantiles[i]}")
    ax[axy, axx].set_ylabel('')
    ax[axy, axx].plot([0,250], [0,250], color='red')
plt.delaxes(ax=ax[1,2])