g4_intro.py

#import libraries

from datetime import datetime, timedelta,date
import pandas as pd
%matplotlib inline
from sklearn.metrics import classification_report,confusion_matrix
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from __future__ import division
from sklearn.cluster import KMeans

import plotly.plotly as py
import plotly.offline as pyoff
import plotly.graph_objs as go

import xgboost as xgb
from sklearn.model_selection import KFold, cross_val_score, train_test_split

#initiate plotly in jupyter notebook
pyoff.init_notebook_mode()

#import the csv
df_data = pd.read_csv('churn_data.csv')

#print first 10 rows
df_data.head(10)