comparison scripts/classification.py @ 65:9b10b688c2ac branch-tests

results for 30 seconds

 import util_feature_learning
 
 
 FILENAMES = map_and_average.OUTPUT_FILES
 TRANSFORM_LABELS = ['LDA', 'PCA', 'NMF', 'SSNMF', 'NA']
+RANDOM_STATE = 12345
 
 def load_data_from_pickle(filename):
     X_list, Y, Yaudio = pickle.load(open(filename,'rb'))
     X = np.concatenate(X_list, axis=1)
     return X, Y, Yaudio
 
 
 def feat_inds_from_pickle(filename):
     X_list, Y, Yaudio = pickle.load(open(filename,'rb'))
-    feat_inds = [len(X_list[0]), len(X_list[1]), len(X_list[2]), len(X_list[3])] 
+    len_inds = np.array([X_list[0].shape[1], X_list[1].shape[1], 
+                         X_list[2].shape[1], X_list[3].shape[1]])
+    cum_sum = np.concatenate([[0], np.cumsum(len_inds)])
+    feat_inds = [np.arange(cum_sum[i], cum_sum[i+1]) for i in range(len(X_list))]
+    #feat_inds = [X_list[0].shape[1], X_list[1].shape[1], X_list[2].shape[1], X_list[3].shape[1]] 
     feat_labels = ['rhy', 'mel', 'mfc', 'chr']
     return feat_labels, feat_inds
 
 
 def get_train_test_indices(audiolabs):

     #traininds, testinds = get_train_test_indices(Yaudio)
     for filename, transform_label in zip(file_list, TRANSFORM_LABELS):
         print filename
         X, Y, Yaudio = load_data_from_pickle(filename)
         #X_train, Y_train, X_test, Y_test = get_train_test_sets(X, Y, traininds, testinds)
-        X_train, X_val_test, Y_train, Y_val_test = train_test_split(X, Y, train_size=0.6, random_state=12345, stratify=Y)
-        X_val, X_test, Y_val, Y_test = train_test_split(X_val_test, Y_val_test, train_size=0.5, random_state=12345, stratify=Y_val_test)
-        df_result = feat_learner.classify(X_train, Y_train, X_test, Y_test, transform_label=transform_label)
-        df_result_feat = classify_each_feature(X_train, Y_train, X_test, Y_test, filename, transform_label=transform_label)
-        df_result = pd.concat([df_result, df_result_feat], axis=1, ignore_index=True)
+        X_train, X_val_test, Y_train, Y_val_test = train_test_split(X, Y, train_size=0.6, random_state=RANDOM_STATE, stratify=Y)
+        X_val, X_test, Y_val, Y_test = train_test_split(X_val_test, Y_val_test, train_size=0.5, random_state=RANDOM_STATE, stratify=Y_val_test)
+        #df_result = feat_learner.classify(X_train, Y_train, X_test, Y_test, transform_label=transform_label)
+        #df_result_feat = classify_each_feature(X_train, Y_train, X_test, Y_test, filename, transform_label=transform_label)
+        #df_result = pd.concat([df_result, df_result_feat], axis=1, ignore_index=True)
+        #df_results = pd.concat([df_results, df_result], axis=0, ignore_index=True)
+        df_result = classify_each_feature(X_train, Y_train, X_test, Y_test, filename, transform_label=transform_label)
         df_results = pd.concat([df_results, df_result], axis=0, ignore_index=True)
     return df_results
 
 
 def classify_each_feature(X_train, Y_train, X_test, Y_test, filename, transform_label=" "):
     n_dim = X_train.shape[1]
     #feat_labels, feat_inds = map_and_average.get_feat_inds(n_dim=n_dim)
     feat_labels, feat_inds = feat_inds_from_pickle(filename)
     #df_results = pd.DataFrame()
+    feat_learner = util_feature_learning.Transformer()
     # first the classification with all features together
     df_results = feat_learner.classify(X_train, Y_train, X_test, Y_test, transform_label=transform_label)
     # 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)
+                                          X_test[:, feat_inds[i]], Y_test, transform_label=transform_label)
         df_results = pd.concat([df_results, df_result], axis=1, ignore_index=True)
     return df_results
 
 
 def plot_CF(CF, labels=None, figurename=None):

     filename = FILENAMES[feat_learning_i]
     print filename
     X, Y, Yaudio = load_data_from_pickle(filename)
     #traininds, testinds = get_train_test_indices(Yaudio)
     #X_train, Y_train, X_test, Y_test = get_train_test_sets(X, Y, traininds, testinds)
-    X_train, X_val_test, Y_train, Y_val_test = train_test_split(X, Y, train_size=0.6, random_state=12345, stratify=Y)
-    X_val, X_test, Y_val, Y_test = train_test_split(X_val_test, Y_val_test, train_size=0.5, random_state=12345, stratify=Y_val_test)
+    X_train, X_val_test, Y_train, Y_val_test = train_test_split(X, Y, train_size=0.6, random_state=RANDOM_STATE, stratify=Y)
+    X_val, X_test, Y_val, Y_test = train_test_split(X_val_test, Y_val_test, train_size=0.5, random_state=RANDOM_STATE, stratify=Y_val_test)
     if output_data:
         _, CF = confusion_matrix(X_train, Y_train, X_test, Y_test, saveCF=True, plots=True)
     else:
         _, CF = confusion_matrix(X_train, Y_train, X_test, Y_test, saveCF=False, plots=False)
     return CF