def train_lr():
params = {
"offline_model_dir": "../weights",
}
params.update(params_common)
X_train, X_valid = load_data("train"), load_data("vali")
X_test = load_data("test")
# print(X_test['label'])
model = LogisticRegression("ranking", params, logger)
model.fit(X_train, validation_data=X_valid)
model.save_session()
model.predict(X_test, 'pred.txt')
def logistic_accuracy(model: LogisticRegression, X: np.ndarray,
targets: np.ndarray):
predictions = model.predict(X) # These are probabilities
predictions = np.around(predictions)
predictions = predictions.reshape(-1)
targets = targets.reshape(-1)
correct = sum(predictions == targets)
return correct / len(targets)
def logistic_loss_function(model: LogisticRegression, X: np.ndarray,
targets: np.ndarray):
"""
Args:
model: Logistic regression model
X: array of pca transformed images
targets: actual labels for the images the predictions are done on
Returns:
The average cross entropy loss over all the predictions
"""
predictions = model.predict(X)
# Error when label equal 1
loss_1 = targets * np.log(predictions)
# Error when label equal 0
loss_0 = (1 - targets) * np.log(1 - predictions)
total_loss = loss_1 + loss_0
# return the average loss overall
return -total_loss.sum() / targets.shape[0]
####################################
# Read and preprocess data from files
####################################
df_train = pd.read_csv(fp_train, skipinitialspace=True)
df_test = pd.read_csv(fp_test, skipinitialspace=True)
df_train['income'].replace('<=50K', 0, inplace=True)
df_train['income'].replace('>50K', 1, inplace=True)
Xtrain, ytrain, Xtest = preprocess(df_train, df_test, features)
####################################
# Train the estimator and predict test data
####################################
regr = []
if estimator == 'logistic':
regr = LogisticRegression().fit(Xtrain, ytrain)
ypred = np.around(regr.predict(Xtest)).astype(int)
elif estimator == 'generative':
regr = NaiveBayes().fit(Xtrain, ytrain)
ypred = regr.predict(Xtest)
####################################
# Write the result to file
####################################
df_pred = pd.DataFrame()
df_pred['id'] = np.arange(1, len(ypred) + 1)
df_pred['label'] = ypred
df_pred.to_csv(fp_ans, index=False)
print('Done')
temp_X_train = np.concatenate((worm_images, noworm_images))
y_train = np.concatenate((worm_label, noworm_label))
print('Shuffling images and labels ...')
X_data, y_data = shuffling_files(temp_X_train, y_train)
print('spliting data .....')
X_train, X_test = data_split(X_data)
y_train, y_test = data_split(y_data)
print('Done')
X_train = X_train / 255
X_test = X_test / 255
model = LogisticRegression(lr=0.02, epochs=500, lamb=8)
tic1 = time.time()
model.fit(X_train, y_train)
toc1 = time.time()
tic2 = time.time()
y_pred = model.predict(X_test)
toc2 = time.time()
y_pred = np.argmax(y_pred, axis=1)
print('Training Time: {}'.format(toc1 - tic1))
print('Testing Time: {}'.format(toc2 - tic2))
print('acc_test: {}'.format(accuracy_score(y_test, y_pred)))
plt.show()
