comparison scripts/classification.py @ 47:081ff4ea7da7 branch-tests

sensitivity experiment split

 def classify_for_filenames(file_list=FILENAMES):
     df_results = pd.DataFrame()
     feat_learner = util_feature_learning.Transformer()
     for filename in file_list:
         X, Y, Yaudio = load_data_from_pickle(filename)
-        traininds, testinds = get_train_test_indices()
+        traininds, testinds = get_train_test_indices(Yaudio)
         X_train, Y_train, X_test, Y_test = get_train_test_sets(X, Y, traininds, testinds)
         df_result = feat_learner.classify(X_train, Y_train, X_test, Y_test)
         df_results = pd.concat([df_results, df_result], axis=0, ignore_index=True)
-    return df_results    
+    return df_results
+
+
+def classify_each_feature(X_train, Y_train, X_test, Y_test):
+    n_dim = X_train.shape[1]
+    feat_labels, feat_inds = map_and_average.get_feat_inds(n_dim=n_dim)
+    #df_results = pd.DataFrame()
+    # first the classification with all features together
+    df_results = feat_learner.classify(X_train, Y_train, X_test, Y_test)
+    # then append for each feature separately
+    for i in range(len(feat_inds)):
+        df_result = feat_learner.classify(X_train[:, feat_inds[i]], Y_train, 
+                                          X_test[:, feat_inds[i]], Y_test)
+        df_results = pd.concat([df_results, df_result], axis=1, ignore_index=True)
+    return df_results
 
 
 def plot_CF(CF, labels=None, figurename=None):
     labels[labels=='United States of America'] = 'United States Amer.'
     plt.imshow(CF, cmap="Greys")