svm handcrafted features

src/svm_hand.py

@@ -0,0 +1,97 @@
+from sklearn.svm import LinearSVC
+from sklearn.base import clone
+from sklearn.pipeline import Pipeline
+from sklearn.model_selection import PredefinedSplit, GridSearchCV
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import classification_report, confusion_matrix, recall_score, make_scorer, plot_confusion_matrix
+# import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+
+RANDOM_SEED = 42
+
+GRID = [
+    {'scaler': [StandardScaler(), None],
+     'estimator': [LinearSVC(random_state=RANDOM_SEED)],
+     'estimator__loss': ['squared_hinge'],
+     'estimator__C': np.logspace(-1, -5, num=5),
+     'estimator__class_weight': ['balanced', None],
+     'estimator__max_iter': [1000]
+     }
+]
+
+PIPELINE = Pipeline([('scaler', None), ('estimator', LinearSVC(dual=True))])
+
+if __name__=='__main__':
+
+    # load handcrafted features and labels
+    devel_X_hand = np.load(
+        "./features/hand_features/x_devel_data.npy", allow_pickle=True
+    )
+
+    test_X_hand = np.load(
+        "./features/hand_features/x_test_data.npy", allow_pickle=True
+    )
+
+    train_X_hand = np.load(
+        "./features/hand_features/x_train_data.npy", allow_pickle=True
+    )
+
+    devel_y = np.load(
+        "./features/hand_features/y_devel_label.npy", allow_pickle=True
+    )
+
+    test_y = np.load(
+        "./features/hand_features/y_test_label.npy", allow_pickle=True
+    )
+
+    train_y = np.load(
+        "./features/hand_features/y_train_label.npy", allow_pickle=True
+    )
+
+    num_train = train_X_hand.shape[0]
+    num_devel = devel_X_hand.shape[0]
+    split_indices = np.repeat([-1, 0], [num_train, num_devel])
+    split = PredefinedSplit(split_indices)
+
+    X = np.append(train_X_hand, devel_X_hand, axis=0)
+    y = np.append(train_y, devel_y, axis=0)
+
+    grid_search = GridSearchCV(estimator=PIPELINE, param_grid=GRID, 
+                                scoring=make_scorer(recall_score, average='macro'), 
+                                n_jobs=-1, cv=split, refit=True, verbose=1, 
+                                return_train_score=False)
+
+    # find best estimator with grid search
+    grid_search.fit(X, y)
+    best_estimator = grid_search.best_estimator_
+
+    # fit clone of best estimator on train for devel predictions
+    estimator = clone(best_estimator, safe=False)
+    estimator.fit(train_X_hand, train_y)
+    preds = estimator.predict(devel_X_hand)
+
+    metrics = {'dev': {}, 'test': {}}
+
+    # devel results
+    print('DEVEL')
+    uar = recall_score(devel_y, preds, average='macro')
+    cm = confusion_matrix(devel_y, preds)
+    print(f'UAR: {uar}\n{classification_report(devel_y, preds)}\n\nConfusion Matrix:\n\n{cm}') 
+    
+    # optional write grid_search to csv file
+    # pd.DataFrame(grid_search.cv_results_).to_csv('grid_search.csv', index=False)
+
+    # test results
+    print('TEST')
+    preds = best_estimator.predict(test_X_hand)
+    uar = recall_score(test_y, preds, average='macro')
+    cm = confusion_matrix(test_y, preds)
+    print(f'UAR: {uar}\n{classification_report(test_y, preds)}\n\nConfusion Matrix:\n\n{cm}') 
+
+    fig = plt.figure()
+    plot_confusion_matrix(best_estimator,X= test_X_hand, y_true=test_y,cmap=plt.cm.Blues,display_labels=['Negative','Positive'],normalize='true')
+    plt.ylabel('True Label')
+    plt.xlabel('Predicated Label')
+    plt.savefig('cm_svm_hand.jpg')