In [1]:

    

from sklearn import ensemble


    

In [4]:

    

from sklearn import cross_validation


    

In [47]:

    

from sklearn import metrics
from sklearn import linear_model


    

In [2]:

    

%matplotlib inline
import pandas as pd
import seaborn as sns
from collections import Counter
from pmareport import pmareport
import numpy as np
import matplotlib.pyplot as plt


    

In [3]:

    

clinic = pmareport.Clinic()
clinic.drop_redundant()


    

In [7]:

    

df = clinic.df


    

In [13]:

    

data = df[['AGE', 'PATIENT_CONDITION', 'SEX', 'INSURANCE_TYPE', 'PROVIDER_NAME']]
responses = df.appt_time


    

In [29]:

    

def make_int(nm):
    categories = list(set(df[nm]))
    df[nm+'i'] = df[nm].apply(lambda x : categories.index(x))


    

In [32]:

    




    

In [30]:

    

for i in ['PATIENT_CONDITION', 'SEX', 'INSURANCE_TYPE', 'PROVIDER_NAME']:
    make_int(i)


    

In [56]:

    

feat = ['AGE', 'PATIENT_CONDITIONi']


    

In [57]:

    

data = df[feat]
responses = df.appt_time


    

In [58]:

    

cv = cross_validation.KFold(len(data), n_folds = 10)


    

In [59]:

    

model = ensemble.RandomForestRegressor()


    

In [60]:

    

for train, test in cv:
    X_train = data.iloc[train]
    X_test = data.iloc[test]
    y_train = responses.iloc[train]
    y_test = responses.iloc[test]
    model.fit(X_train, y_train)
    pred = model.predict(X_test)
    print metrics.regression.mean_squared_error(y_true=y_test, y_pred=pred)


    

    




6.42061211569
6.54205812407
5.7141137378
5.93013043853
6.08116550354
6.35753793651
6.37316595341
6.83181778258
5.61663102621
6.35848447564

In [1]:

    




    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-458d5f1afc81> in <module>()
----> 1 model

NameError: name 'model' is not defined

In [42]:

    




    

In [ ]: