In [1]:

    

%load_ext autoreload
%autoreload 2
%matplotlib inline


    

In [2]:

    

from munging import session
from munging import transform


import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

from sklearn.metrics import f1_score, roc_auc_score
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.linear_model import LogisticRegression


    

In [23]:

    

## load data
data = pd.read_csv("data/amazon_employee_access/train.csv")
## make ids recognized as categorical data
for f in data.columns[1:]:
    data[f] = data[f].astype(np.str)
data.head(3)


    

    
Out[23]:






  

    

      

      
ACTION
      
RESOURCE
      
MGR_ID
      
ROLE_ROLLUP_1
      
ROLE_ROLLUP_2
      
ROLE_DEPTNAME
      
ROLE_TITLE
      
ROLE_FAMILY_DESC
      
ROLE_FAMILY
      
ROLE_CODE
    
  
  

    

      
0
      
 1
      
 39353
      
 85475
      
 117961
      
 118300
      
 123472
      
 117905
      
 117906
      
 290919
      
 117908
    
    

      
1
      
 1
      
 17183
      
  1540
      
 117961
      
 118343
      
 123125
      
 118536
      
 118536
      
 308574
      
 118539
    
    

      
2
      
 1
      
 36724
      
 14457
      
 118219
      
 118220
      
 117884
      
 117879
      
 267952
      
  19721
      
 117880
    
  

In [25]:

    

## exploration session
dsession = session.Session(data, "ACTION", random_state=0)
transformers = []
print dsession.get_parameters()


    

    




{'SKEWNESS_THR': 20, 'FRAC_OF_NA_TO_IGNORE': 0.95, 'FRAC_OF_FEAT_TO_BE_NONINFORMATIVE': 0.96, 'REDUNDANT_FEAT_CORR_THR': 0.95, 'MIN_NUM_VALUES_FOR_NUMERICAL': 5}

In [26]:

    

## numerical and categorical features
numerical_feats = dsession.get_features_of(dsession.is_numerical_feature)
categorical_feats = dsession.get_features_of(dsession.is_categorical_feature)
print len(numerical_feats)
print len(categorical_feats)


    

    




0
9

In [28]:

    

## knowing what you are dealing with
pd.value_counts(data.ACTION) * 1./ data.shape[0]


    

    
Out[28]:





1    0.94211
0    0.05789
dtype: float64

In [ ]: