comparison scripts/classification.py @ 62:4425a4918102 branch-tests

fixed indices for feature components

 """
 import numpy as np
 import pandas as pd
 import pickle
 from sklearn import metrics
+from sklearn.model_selection import train_test_split
 
 import map_and_average
 import util_feature_learning
 
 

 
 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])] 
+    feat_labels = ['rhy', 'mel', 'mfc', 'chr']
+    return feat_labels, feat_inds
 
 
 def get_train_test_indices(audiolabs):
     trainset, valset, testset = map_and_average.load_train_val_test_sets()
     trainaudiolabels, testaudiolabels = trainset[2], testset[2]

         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, 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)
     return df_results
 
 
-def classify_each_feature(X_train, Y_train, X_test, Y_test, transform_label=" "):
+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 = map_and_average.get_feat_inds(n_dim=n_dim)
+    feat_labels, feat_inds = feat_inds_from_pickle(filename)
     #df_results = pd.DataFrame()
     # 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)):