g_series_7_intro.py

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 #must if you use python 2
from sklearn.cluster import KMeans

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

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

#initate plotly 
pyoff.init_notebook_mode()

#function for ordering cluster numbers for given criteria
def order_cluster(cluster_field_name, target_field_name,df,ascending):
    new_cluster_field_name = 'new_' + cluster_field_name
    df_new = df.groupby(cluster_field_name)[target_field_name].mean().reset_index()
    df_new = df_new.sort_values(by=target_field_name,ascending=ascending).reset_index(drop=True)
    df_new['index'] = df_new.index
    df_final = pd.merge(df,df_new[[cluster_field_name,'index']], on=cluster_field_name)
    df_final = df_final.drop([cluster_field_name],axis=1)
    df_final = df_final.rename(columns={"index":cluster_field_name})
    return df_final

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

#print first 10 rows
df_data.head(10)