def gradient_descent_linear_regression(train_data, learning_rate):
# Add bias term in training data
train_data_with_bias = add_bias_term_in_data(train_data)
predicted_y = []
tetas = initialize_tetas(len(train_data_with_bias[0]) - 1)
if (len(train_data_with_bias)):
cost_arr = []
iteration = []
tetas, change_in_tetas = one_training_iteration(
train_data_with_bias, tetas, learning_rate,
len(train_data_with_bias))
for i in range(1000):
tetas, change_in_tetas = one_training_iteration(
train_data_with_bias, tetas, learning_rate,
len(train_data_with_bias))
print("Iteration %d", (i + 1))
cost = compute_cost(train_data_with_bias, tetas)
print("Cost: %(key1)s" % {'key1': cost})
iteration.append(i + 1)
cost_arr.append(cost)
for i in range(len(train_data_with_bias)):
predicted_y.append(predict_instance(train_data_with_bias[i],
tetas))
#print("predicted value %(key1)s Actual value %(key2)s"%{'key1':predict_instance(train_data_with_bias[i],tetas),'key2':train_data_with_bias[i][len(train_data_with_bias[0])-1]})
plot_linear_regression_with_one_variable(train_data, predicted_y)
plot_cost_function(iteration, cost_arr)
else:
print("No training data")
return predicted_y, tetas
def gradient_descent_logistic_regression(train_data, learning_rate):
# Add bias term in training data
train_data, mean, std_dev = normalize_features(train_data)
train_data_with_bias = add_bias_term_in_data(train_data)
predicted_y = []
tetas = initialize_tetas(len(train_data_with_bias[0]) - 1)
if (len(train_data_with_bias)):
tetas = one_training_iteration(train_data_with_bias,
tetas, learning_rate,
len(train_data_with_bias))
print(tetas)
for i in range(1000):
tetas = one_training_iteration(train_data_with_bias, tetas,
learning_rate,
len(train_data_with_bias))
print("Iteration: %(key1)s" % {'key1': i + 1})
cost = compute_cost(train_data_with_bias, tetas)
print("Cost: %(key1)s" % {'key1': cost})
legends = ['Admitted', 'Not Admitted', 'Decision Boundary']
titles = [
"Exam 1 Score", "Exam 2 Score",
"Traning Data with decision boundary"
]
plotTrainingData(train_data, tetas, titles, legends)
else:
print("No training data")
return tetas, mean, std_dev
def training(train_data):
temp_X = [row[:-1] for row in train_data]
Y = np.array([row[-1] for row in train_data])
X = add_bias_term_in_data(temp_X)
X_t = X.transpose()
X_mul_X_t = X_t.dot(X)
tetas = inv(X_mul_X_t).dot(X_t).dot(Y)
"""print(X)
print(Y)
print(tetas)"""
print(predict_instance([1, 1650, 3], tetas))
return tetas
def main():
#ex1data1.
train_data = loadData('data/ex1data2.txt')
#evaluateModels(train_data)
tetas, mean, std_dev, predicted_y = gradient_descent_linear_regression(
train_data, 0.5)
test_data = loadData('data/testdata.txt')
test_data = normalize_test_data(test_data, mean, std_dev)
test_data = add_bias_term_in_data(test_data)
print("Start predicting new instances")
for i in range(len(test_data)):
predicted_value = predict_instance(test_data[i], tetas)
print("value of instance %(key1)s is %(key2)s" % {
'key1': i + 1,
'key2': predicted_value
})
def main():
#ex1data1.
train_data = loadData('data2/ex2data1.txt')
legends = ['Admitted', 'Not Admitted']
titles = ["Exam 1 Score", "Exam 2 Score", "Scatter Plot of training data"]
plotTrainingData(train_data, [], titles, legends)
#train_data = [[0,0,0],[0,1,1],[1,0,1],[1,1,1]]
tetas, mean, std_dev = gradient_descent_logistic_regression(
train_data, 0.8)
test_data = [[45, 85, 1]]
test_data = normalize_test_data(test_data, mean, std_dev)
test_data = add_bias_term_in_data(test_data)
for i in range(len(test_data)):
predicted_value = predict_instance(test_data[i], tetas)
print("Probability of Test Example is %(key2)s" % {
'key1': i + 1,
'key2': predicted_value
})
def predict_test_data(test_data,tetas):
test_data_with_bias = add_bias_term_in_data(test_data)
predicted_y = []
for i in range(len(test_data_with_bias)):
predicted_y.append(predict_instance(test_data_with_bias[i],tetas))
return predicted_y