tick_marks = np.arange(len(CM_LABELS)) plt.xticks(tick_marks, CM_LABELS, rotation=45) plt.yticks(tick_marks, CM_LABELS) plt.tight_layout() plt.ylabel('True label') plt.xlabel('Predicted label') NUM_PER_CATEGORY = 5500 print('loading data....') print(str(NUM_PER_CATEGORY) + ' examples per category') start_time = time.time() # images, labels = prep.get_crowdflower(NUM_PER_CATEGORY) images, labels = prep.get_data(NUM_PER_CATEGORY) images = images.astype('float32') train_x, test_x, train_y, test_y = train_test_split( images, labels, train_size=.7, random_state=20160319) print('Total data load time:') print('---------------------') print(time.time() - start_time) os.system('say "data is loaded"') # Consider trying different values for output_layers print('\nstarting nn on twitter with logit @ -2....') tf = OverfeatTransformer(output_layers=[-2]) clf = LogisticRegression() # clf = SVC() # clf = RandomForestClassifier() pipe = make_pipeline(tf, clf) start_time = time.time()
print(__doc__) from sklearn_theano.datasets import fetch_asirra from sklearn_theano.feature_extraction import OverfeatTransformer from sklearn_theano.utils import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.pipeline import make_pipeline from sklearn.metrics import classification_report, accuracy_score import matplotlib.pyplot as plt import time asirra = fetch_asirra(image_count=20) X = asirra.images.astype('float32') y = asirra.target X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=.6, random_state=1999) tf = OverfeatTransformer(output_layers=[-3]) clf = LogisticRegression() pipe = make_pipeline(tf, clf) t0 = time.time() pipe.fit(X_train, y_train) print("Total transform time") print("====================") print(time.time() - t0) print() y_pred = pipe.predict(X_test) print(classification_report(y_test, y_pred)) print() print("Accuracy score") print("==============")
""" print(__doc__) from sklearn_theano.datasets import fetch_asirra from sklearn_theano.feature_extraction import OverfeatTransformer from sklearn_theano.utils import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.pipeline import make_pipeline from sklearn.metrics import classification_report, accuracy_score import matplotlib.pyplot as plt import time asirra = fetch_asirra(image_count=20) X = asirra.images.astype('float32') y = asirra.target X_train, X_test, y_train, y_test = train_test_split( X, y, train_size=.6, random_state=1999) tf = OverfeatTransformer(output_layers=[-3]) clf = LogisticRegression() pipe = make_pipeline(tf, clf) t0 = time.time() pipe.fit(X_train, y_train) print("Total transform time") print("====================") print(time.time() - t0) print() y_pred = pipe.predict(X_test) print(classification_report(y_test, y_pred)) print() print("Accuracy score") print("==============") print(accuracy_score(y_test, y_pred))