Merge pull request #3 from anujonthemove/master

chrisclark · web-flow · commit ce8da861c933 · 2016-10-21T15:48:07.000-07:00
updated file parser, n_folds=5, n_jobs=-1
diff --git a/crossValidate.py b/crossValidate.py
@@ -2,28 +2,32 @@
 from sklearn import cross_validation
 import logloss
 import numpy as np
+import pandas as pd
+from sklearn.preprocessing import Imputer
 
 def main():
     #read in  data, parse into training and target sets
-    dataset = np.genfromtxt(open('Data/train.csv','r'), delimiter=',', dtype='f8')[1:]    
-    target = np.array([x[0] for x in dataset])
-    train = np.array([x[1:] for x in dataset])
+    dataset = pd.read_csv('Data/train.csv')
+    target = dataset.Activity.values
+    train = dataset.drop('Activity', axis=1).values
+    imp = Imputer(missing_values = 'NaN',strategy='mean',axis=0)
+    new_train_data = imp.fit_transform(train)
 
     #In this case we'll use a random forest, but this could be any classifier
-    cfr = RandomForestClassifier(n_estimators=100)
+    cfr = RandomForestClassifier(n_estimators=100, n_jobs=-1)
 
     #Simple K-Fold cross validation. 5 folds.
-    cv = cross_validation.KFold(len(train), k=5, indices=False)
+    cv = cross_validation.KFold(len(new_train_data), n_folds=5, indices=False)
 
     #iterate through the training and test cross validation segments and
     #run the classifier on each one, aggregating the results into a list
     results = []
     for traincv, testcv in cv:
-        probas = cfr.fit(train[traincv], target[traincv]).predict_proba(train[testcv])
+        probas = cfr.fit(new_train_data[traincv], target[traincv]).predict_proba(new_train_data[testcv])
         results.append( logloss.llfun(target[testcv], [x[1] for x in probas]) )
 
     #print out the mean of the cross-validated results
     print "Results: " + str( np.array(results).mean() )
 
 if __name__=="__main__":
-    main()
+    main()
