'''Import basic modules'''
import pandas as pd
import numpy as np
import string
from sklearn.model_selection import KFold, StratifiedKFold, cross_val_score
from sklearn.metrics import roc_auc_score as auc
from sklearn.linear_model import LogisticRegression, SGDClassifier

'''import visualization'''
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style("ticks")
%matplotlib inline

import matplotlib.gridspec as gridspec

'''Plotly visualization .'''
import plotly.offline as py
import plotly.graph_objs as go
import plotly.tools as tls
py.init_notebook_mode(connected=True)

'''Display markdown formatted output like bold, italic bold etc.'''
from IPython.display import Markdown
def bold(string):
    display(Markdown(string))

'''Ignore deprecation and future, and user warnings.'''
import warnings as wrn
wrn.filterwarnings('ignore', category = DeprecationWarning) 
wrn.filterwarnings('ignore', category = FutureWarning) 
wrn.filterwarnings('ignore', category = UserWarning) 

# Load data
train = pd.read_csv('../Desktop/android_bids_us.csv')
print(train.shape)

from pandas_profiling import ProfileReport
import matplotlib.gridspec as gridspec
profile = ProfileReport(train, minimal=True)
profile

#Variable Description
def description(df):
    print(f"Dataset Shape: {df.shape}")
    summary = pd.DataFrame(df.dtypes,columns=['dtypes'])
    summary = summary.reset_index()
    summary['Name'] = summary['index']
    summary = summary[['Name','dtypes']]
    summary['Missing'] = df.isnull().sum().values    
    summary['Uniques'] = df.nunique().values
    summary['First Value'] = df.iloc[0].values
    summary['Second Value'] = df.iloc[1].values
    summary['Third Value'] = df.iloc[2].values
    return summary
bold('**Variable Description of  train Data:**')
description(train)

# Replacing missing values by the most repeat data(mod)e in the colomns 

def replace_nan(data):
    for column in data.columns:
        if data[column].isna().sum() > 0:
            data[column] = data[column].fillna(data[column].mode()[0])


replace_nan(train)