import numpy as np
import pandas as pd
import warnings
warnings.filterwarnings('ignore')
from dateutil.parser import parse
import matplotlib.pyplot as plt
import seaborn as sns
from IPython.display import Markdown, display ,HTML
pd.set_option('display.max_columns',200)
pd.set_option('display.max_rows',300)

sns.set_style('dark')
#Model related packages 
import sklearn
from sklearn.model_selection import train_test_split # for splitting train & test data set
from sklearn.preprocessing import StandardScaler # for scaling
import statsmodels.api as sm_1 # for modelling
from statsmodels.stats.outliers_influence import variance_inflation_factor # for VIF computation
from sklearn.metrics import r2_score,classification_report # for prediction

from sklearn.model_selection import GridSearchCV
# Importing RFE and Logistic Regression
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
from sklearn.metrics import precision_recall_curve
#for pca
from sklearn.decomposition import PCA, IncrementalPCA
#from sklearn.decomposition import 
#for decison tree
from IPython.display import Image  
from sklearn.externals.six import StringIO  
from sklearn.tree import export_graphviz
import pydotplus, graphviz
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
#for logistic with pca
from sklearn.pipeline import Pipeline
#random forest
from sklearn.ensemble import RandomForestClassifier

data = pd.read_csv('telecom_churn_data.csv')
data.head()

#check for duplicates
sum(data.duplicated(subset = 'mobile_number')) == 0