# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

#file ="../input/quant/df_mi"
file ="../input/quant/df_scale_finale"
df = pd.read_csv(file)
df.head()

import numpy as np
import pandas as pd
import warnings

## Plotting libraries
import seaborn as sns
import matplotlib.pyplot as plt

## Sklearn Libraries
from sklearn.utils import shuffle
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer
from sklearn.metrics import f1_score, confusion_matrix, roc_curve, auc, \
            classification_report, recall_score, precision_recall_curve

# Define random state
random_state = 2018
np.random.seed(random_state)
warnings.filterwarnings('ignore')

# latex parameter
font = {
    'family': 'serif', 
    'serif': ['Computer Modern Roman'],
    'weight' : 'regular',
    'size'   : 14
    }

plt.rc('font', **font)