def main():
df, X, y = preprocess_data()
X_train, X_test, y_train, y_test = train_test_splitter(X=X, y=y, ratio=0.8)
logistic_regressor = LogisticRegressor(alpha=0.05,
c=0.01,
T=1000,
random_seed=0,
intercept=True)
losses = logistic_regressor.fit(X_train, y_train)
plot_losses(losses=losses, savefig=True)
train_error = error_rate(y_train, logistic_regressor.predict(X_train))
test_error = error_rate(y_test, logistic_regressor.predict(X_test))
print('Training Error Rate: %f' % train_error)
print('Test Error Rate: %f' % test_error)
[0, 0, ['mayo', 'jelly'], 0], [5, 0, [], 4], [5, 0, ['mayo'], 8],
[5, 0, ['jelly'], 1], [5, 0, ['mayo', 'jelly'], 0], [0, 5, [], 5],
[0, 5, ['mayo'], 0], [0, 5, ['jelly'], 9], [0, 5, ['mayo', 'jelly'], 0],
[5, 5, [], 0], [5, 5, ['mayo'], 0], [5, 5, ['jelly'], 0],
[5, 5, ['mayo', 'jelly'], 0]],
columns=['beef', 'pb', 'condiments', 'rating'])
df = df.create_dummy_variables('condiments')
df = df.create_interaction_terms('beef', 'pb')
df = df.create_interaction_terms('beef', 'mayo')
df = df.create_interaction_terms('beef', 'jelly')
df = df.create_interaction_terms('pb', 'mayo')
df = df.create_interaction_terms('pb', 'jelly')
df = df.create_interaction_terms('mayo', 'jelly')
log_df = DataFrame(df.data_dict, df.columns)
logistic_regressor = LogisticRegressor(log_df, 10, dependent_variable='rating')
# test 8 slices of beef + mayo
observation = {'beef': 8, 'mayo': 1}
assert round(logistic_regressor.predict(observation), 2) == 9.72
# test 4 tbsp of pb + 8 slices of beef + mayo
observation = {'beef': 8, 'pb': 4, 'mayo': 1}
assert round(logistic_regressor.predict(observation), 2) == 0.77
# test 8 slices of beef + mayo + jelly
observation = {'beef': 8, 'mayo': 1, 'jelly': 1}
assert round(logistic_regressor.predict(observation), 2) == 0.79
['mayo', 'jelly'], [], ['mayo'], ['jelly'],
['mayo', 'jelly']],
'rating': [1, 1, 4, 0, 4, 8, 1, 0, 5, 0, 9, 0, 0, 0, 0, 0]
}
df = DataFrame(data_dict, column_order=['beef', 'pb', 'condiments'])
df = df.create_dummy_variables()
df = df.append_pairwise_interactions()
df = df.append_columns({
'constant': [1 for _ in range(len(data_dict['rating']))],
'rating': data_dict['rating']
})
df = df.apply('rating', lambda x: 0.1 if x == 0 else x)
regressor = LogisticRegressor(df, prediction_column='rating', max_val=10)
assert regressor.multipliers == [
-0.039, -0.0205, 1.7483, -0.3978, 0.1497, -0.7485, 0.4682, 0.3296, -0.5288,
2.6441, 1.0125
], 'Wong multipliers'
assert regressor.predict({
'beef': 5,
'pb': 5,
'mayo': 1,
'jelly': 1,
}) == 0.02342, 'Nah bruh'
assert regressor.predict({
'beef': 0,
'pb': 3,
print 'Plotting data with green circle indicating (y=1) examples and red circle indicating (y=0) examples ...'
plot_utils.plot_twoclass_data(X,y,'Exam 1 score', 'Exam 2 score',['Not Admitted','Admitted'])
plt.savefig('fig1.pdf')
########################################################################
##================ Part 1: Compute cost and gradient ==================#
########################################################################
# set up the X matrix with the column of ones as intercept
XX = np.vstack([np.ones((X.shape[0],)),X.T]).T
# set up a logistic regression model
log_reg1 = LogisticRegressor()
# test the loss and gradient function
theta = np.zeros((XX.shape[1],))
loss = log_reg1.loss(theta,XX,y)
print "Loss on all-zeros theta vector (should be around 0.693) = ", loss
grad = log_reg1.grad_loss(theta,XX,y)
print "Gradient of loss wrt all-zeros theta vector (should be around [-0.1, -12.01, -11.26]) = ", grad
# run fmin on the loss function and gradient implemented in logistic_regressor.py
theta_opt = log_reg1.train(XX,y,num_iters=400)
# print the theta found
from dataframe import DataFrame
from logistic_regressor import LogisticRegressor
students_dict = {
'ACT': [33, 34, 35, 30, 36, 29, 36, 31, 36, 32],
'extra': [1, 0, 1, 1, 1, 1, 1, 1, 0, 0],
'Bias': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
}
students_dict.update({
'interaction': [
students_dict['ACT'][i] * students_dict['extra'][i]
for i in range(len(students_dict['ACT']))
]
})
students_dict.update({
'accepted':
[0.95, 0.001, 0.95, 0.001, 0.95, 0.001, 0.95, 0.001, 0.95, 0.001]
})
df = DataFrame(students_dict)
regressor = LogisticRegressor(df, 'accepted', 0.999)
# predictor = {'ACT': 36, 'extra': 0}
# df_bruh = DataFrame(predictor)
# print(df_bruh.gather_all_inputs())
# print(regressor.predict(predictor))
print(regressor.multipliers)
delta_table = [0.1, 0.01, 0.001, 0.0001]
all_coords = []
for delta_low in delta_table:
# new_list=[]
# for pair in list_data:
# if pair[1] == 0:
# new_list.append([pair[0],delta])
# else:
# new_list.append([pair[0],1-delta])
df = DataFrame.from_array(list_data, columns=['x', 'y'])
regressor = LogisticRegressor(df,
prediction_column='y',
max_value=1,
delta=delta_low)
coords = [[], []]
for x in range(20):
coords[0].append(x / 100)
coords[1].append(regressor.predict({'constant': 1, 'x': x}))
all_coords.append(coords)
print(all_coords)
plt.style.use('bmh')
for coords in all_coords:
plt.plot(coords[0], coords[1], linewidth=2.5)
plt.legend(['0.1', '0.01', '0.001', '0.0001'])
plt.savefig('logistic_regressor_109.png')
# dfgd = DataFrame.from_array(
reg = LogisticRegressor(df, dependent_variable='y', premade = True)
reg.set_coefficients({'constant': 0.5, 'x': 0.5})
print(reg.calc_rss())
print(reg.calc_gradient(delta))
reg.gradient_descent(alpha, delta, num_steps)
print(reg.coefficients)
'''
df = DataFrame.from_array([[2, 1], [3, 0]], columns=['x', 'y'])
alpha = 0.2
delta = 0.1
num_steps = 20000
reg = LogisticRegressor(df, dependent_variable='y', premade=True)
reg.set_coefficients({'constant': 1, 'x': 1})
print(reg.calc_rss())
print(reg.calc_gradient(delta))
#reg.gradient_descent(alpha, delta, num_steps)
#print(reg.coefficients)
''''
import matplotlib.pyplot as plt
plt.style.use('bmh')
points = {'x': [], 'y': []}
x = -5
print('regressor with interaction terms')
print(regressor.coefficients)
print(regressor.predict({'beef': 5, 'pb': 0, 'beef * pb': 0}))
print(regressor.predict({'beef': 5, 'pb': 5, 'beef * pb': 25}))
df = DataFrame.from_array(
[[0, 0, 1], [1, 0, 2], [2, 0, 4], [4, 0, 8], [6, 0, 9], [0, 2, 2],
[0, 4, 5], [0, 6, 7], [0, 8, 6], [2, 2, 0.1], [3, 4, 0.1]],
columns=['beef', 'pb', 'rating'])
df = df.create_interaction_terms('beef', 'pb')
regressor = LogisticRegressor(df, 'rating', 10)
print('Logistic regressor with interaction terms')
print(regressor.coefficients)
print(regressor.predict({'beef': 5, 'pb': 0, 'beef * pb': 0}))
print(regressor.predict({'beef': 12, 'pb': 0, 'beef * pb': 0}))
print(regressor.predict({'beef': 5, 'pb': 5, 'beef * pb': 25}))
print('-----------Assignment 52-----------')
df = DataFrame.from_array(
[[0, 0, [], 1], [0, 0, ['mayo'], 1], [0, 0, ['jelly'], 4],
[0, 0, ['mayo', 'jelly'], 0], [5, 0, [], 4], [5, 0, ['mayo'], 8],
print 'Plotting data with green circle indicating (y=1) examples and red circle indicating (y=0) examples ...'
plot_utils.plot_twoclass_data(X,y,'Exam 1 score', 'Exam 2 score',['Not Admitted','Admitted'])
plt.savefig('fig1.pdf')
########################################################################
##================ Part 1: Compute cost and gradient ==================#
########################################################################
# set up the X matrix with the column of ones as intercept
XX = np.vstack([np.ones((X.shape[0],)),X.T]).T
# set up a logistic regression model
log_reg1 = LogisticRegressor()
# test the loss and gradient function
theta = np.zeros((XX.shape[1],))
loss = log_reg1.loss(theta,XX,y)
print "Loss on all-zeros theta vector (should be around 0.693) = ", loss
grad = log_reg1.grad_loss(theta,XX,y)
print "Gradient of loss wrt all-zeros theta vector (should be around [-0.1, -12.01, -11.26]) = ", grad
# run fmin on the loss function and gradient implemented in logistic_regressor.py
theta_opt = log_reg1.train(XX,y,num_iters=400)
# print the theta found
import matplotlib.pyplot as plt
plt.style.use('bmh')
import sys
sys.path.append('src')
from dataframe import DataFrame
from linear_regressor import LinearRegressor
from logistic_regressor import LogisticRegressor
arr = [[1, 0], [2, 0], [3, 0], [2, 1], [3, 1], [4, 1]]
df = DataFrame.from_array(arr, columns=['x', 'y'])
'''
python tests/test_regressors.py
'''
reg = LogisticRegressor(df, dependent_variable='y', upper_bound=1)
reg.set_coefficients({'constant': 0.5, 'x': 0.5})
alpha = 0.01
delta = 0.01
num_steps = 20000
reg.gradient_descent(alpha, delta, num_steps)
print("\nreg.coefficients:",
reg.coefficients) # should be {'constant': 2.7911, 'x': -1.1165}
x = [pair[0] for pair in arr]
y = [pair[1] for pair in arr]
lots_of_xs = [x / 100 for x in range(100, 401)]
prediction = [reg.predict({'x': x}) for x in lots_of_xs]
'condiments': [[], ['mayo'], ['jelly'], ['mayo', 'jelly'], [], ['mayo'],
['jelly'], ['mayo', 'jelly'], [], ['mayo'], ['jelly'],
['mayo', 'jelly'], [], ['mayo'], ['jelly'],
['mayo', 'jelly']],
'rating': [1, 1, 4, 0, 4, 8, 1, 0, 5, 0, 9, 0, 0, 0, 0, 0]
}
df = DataFrame(data_dict, column_order=['beef', 'pb', 'condiments'])
df = df.create_dummy_variables()
df = df.append_pairwise_interactions()
df = df.append_columns({
'constant': [1 for _ in range(len(data_dict['beef']))],
'rating': [1, 1, 4, 0, 4, 8, 1, 0, 5, 0, 9, 0, 0, 0, 0, 0]
})
df = df.apply('rating', lambda x: 0.1 if x == 0 else x)
regressor = LogisticRegressor(df, prediction_column='rating', max_value=10)
# print("\n Testing multipliers")
# assert regressor.multipliers == {
# 'beef': -0.03900793,
# 'pb': -0.02047944,
# 'mayo': 1.74825378,
# 'jelly': -0.39777219,
# 'beef_pb': 0.14970983,
# 'beef_mayo': -0.74854916,
# 'beef_jelly': 0.46821312,
# 'pb_mayo': 0.32958369,
# 'pb_jelly': -0.5288267,
# 'mayo_jelly': 2.64413352,
# 'constant': 1.01248436
# }, 'Incorrect multipliers an is instead:'+str(regressor.multipliers)
if index in dataframe_indices]
dataframe.append_columns({'constant': [1 for _ in dataframe_indices]})
linear_regressor = LinearRegressor(dataframe,
ratings,
prediction_column='Survived')
linear_regressor.solve_coefficients()
linear_regressor_classifications = get_classifications(linear_regressor,
testing_dataframe)
for row in linear_regressor_classifications:
print(row)
print('\n')
logistic_regressor = LogisticRegressor(dataframe,
ratings,
prediction_column='Survived')
logistic_regressor.solve_coefficients()
logistic_regressor_classifications = get_classifications(
logistic_regressor, testing_dataframe)
for row in logistic_regressor_classifications:
print(row)
dataframe.remove_columns(['constant'])
dataframe.append_columns({
'Survived': [
did_survive for index, did_survive in enumerate(survived_people)
if index in dataframe_indices
]
})
}
df = DataFrame(data_dict,
column_order=['percentile', 'ACT', 'extracurricular'])
# print(df.ordered_dict)
df = df.append_pairwise_interactions()
# print(df.ordered_dict)
df = df.append_columns({
'constant': [1 for _ in range(len(data_dict['percentile']))],
'acceptance':
[0.999, 0.001, 0.999, 0.001, 0.999, 0.001, 0.999, 0.001, 0.999, 0.001]
})
# print(df.ordered_dict)
df = df.apply('acceptance', lambda x: 0.1 if x == 0 else x)
# print(df.ordered_dict)
regressor = LogisticRegressor(df, prediction_column='acceptance', max_value=1)
print(regressor.coefficients)
print(
"Martha: " +
str(regressor.predict({
'percentile': 95,
'ACT': 33,
'extracurricular': 1
})))
print(
"Jeremy: " +
str(regressor.predict({
'percentile': 95,
'ACT': 34,
'extracurricular': 0
})))
import sys
sys.path.append('src')
from logistic_regressor import LogisticRegressor
from dataframe import DataFrame
data = [[10, 0.05], [100, 0.35], [1000, 0.95]]
df = DataFrame.from_array(data, ['x', 'y'])
regressor = LogisticRegressor(df, 'y', 1)
print(regressor.coefficients)
print(regressor.predict({'x': 500}))
import sys
sys.path.append('src')
from matrix import Matrix
from dataframe import DataFrame
from linear_regressor import LinearRegressor
from logistic_regressor import LogisticRegressor
df = DataFrame.from_array(
[[0, 0, 1, 0],
[1, 0, 2, 0],
[2, 0, 4, 0],
[4, 0, 8, 0],
[6, 0, 9, 0],
[0, 2, 2, 0],
[0, 4, 5, 0],
[0, 6, 7, 0],
[0, 8, 6, 0],
[2, 2, 0.1, 4],
[3, 4, 0.1, 12]],
columns = ['beef', 'pb', 'rating', 'interactive']
)
log_reg = LogisticRegressor(df,10, dependent_variable = 'rating')
print(log_reg.predict({'beef': 5, 'pb': 0 , 'interactive':0}))
print(log_reg.predict({'beef': 12, 'pb': 0 , 'interactive':0}))
print(log_reg.predict({'beef': 5, 'pb': 5 , 'interactive':25}))
print(linear_regressor.predict({'beef': 0, 'pb': 4 , 'mayo': 1, 'jelly': 0, 'beef * pb': 0, 'beef * mayo': 0, 'beef * jelly': 0, 'pb * mayo': 4, 'pb * jelly': 0, 'mayo * jelly': 0}))
print(linear_regressor.predict({'beef': 8, 'pb': 4 , 'mayo': 1, 'jelly': 0, 'beef * pb': 32, 'beef * mayo': 8, 'beef * jelly': 0, 'pb * mayo': 4, 'pb * jelly': 0, 'mayo * jelly': 0}))
print(linear_regressor.predict({'beef': 8, 'pb': 0 , 'mayo': 1, 'jelly': 1, 'beef * pb': 0, 'beef * mayo': 8, 'beef * jelly': 8, 'pb * mayo': 0, 'pb * jelly': 0, 'mayo * jelly': 1}))'''
df = DataFrame.from_array(
[[0, 0, [], 1], [0, 0, ['mayo'], 1], [0, 0, ['jelly'], 4],
[0, 0, ['mayo', 'jelly'], 0], [5, 0, [], 4], [5, 0, ['mayo'], 8],
[5, 0, ['jelly'], 1], [5, 0, ['mayo', 'jelly'], 0], [0, 5, [], 5],
[0, 5, ['mayo'], 0], [0, 5, ['jelly'], 9], [0, 5, ['mayo', 'jelly'], 0],
[5, 5, [], 0], [5, 5, ['mayo'], 0], [5, 5, ['jelly'], 0],
[5, 5, ['mayo', 'jelly'], 0]],
columns=['beef', 'pb', 'condiments', 'rating'])
df = df.create_dummy_variables('condiments')
df = df.create_interaction_terms('beef', 'pb')
df = df.create_interaction_terms('beef', 'mayo')
df = df.create_interaction_terms('beef', 'jelly')
df = df.create_interaction_terms('pb', 'mayo')
df = df.create_interaction_terms('pb', 'jelly')
df = df.create_interaction_terms('mayo', 'jelly')
log_df = DataFrame(df.data_dict, df.columns)
logistic_regressor = LogisticRegressor(log_df, 10, dependent_variable='rating')
'''
print('logistic_regressor')
print(logistic_regressor.predict({'beef': 8, 'pb': 0 , 'mayo': 1, 'jelly': 0, 'beef * pb': 0, 'beef * mayo': 8, 'beef * jelly': 0, 'pb * mayo': 0, 'pb * jelly': 0, 'mayo * jelly': 0}))
print(logistic_regressor.predict({'beef': 0, 'pb': 4 , 'mayo': 0, 'jelly': 1, 'beef * pb': 0, 'beef * mayo': 0, 'beef * jelly': 0, 'pb * mayo': 0, 'pb * jelly': 4, 'mayo * jelly': 0}))
print(logistic_regressor.predict({'beef': 0, 'pb': 4 , 'mayo': 1, 'jelly': 0, 'beef * pb': 0, 'beef * mayo': 0, 'beef * jelly': 0, 'pb * mayo': 4, 'pb * jelly': 0, 'mayo * jelly': 0}))
print(logistic_regressor.predict({'beef': 8, 'pb': 4 , 'mayo': 1, 'jelly': 0, 'beef * pb': 32, 'beef * mayo': 8, 'beef * jelly': 0, 'pb * mayo': 4, 'pb * jelly': 0, 'mayo * jelly': 0}))
print(logistic_regressor.predict({'beef': 8, 'pb': 0 , 'mayo': 1, 'jelly': 1, 'beef * pb': 0, 'beef * mayo': 8, 'beef * jelly': 8, 'pb * mayo': 0, 'pb * jelly': 0, 'mayo * jelly': 1}))'''
assert len(train_imgs) + len(val_imgs) == n_imgs
trafos = [utils.to_channel_first, utils.normalize, utils.to_tensor]
trafos = partial(utils.compose, transforms=trafos)
train_data = utils.DatasetWithTransform(train_imgs,
train_labels,
transform=trafos)
val_data = utils.DatasetWithTransform(val_imgs, val_labels, transform=trafos)
print("N Training: ", len(train_imgs))
print("N Val: ", len(val_imgs))
n_pixels = images[0].size
n_classes = 10
model = LogisticRegressor(n_pixels, n_classes)
model.to(device)
train_batch_size = 4
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=train_batch_size,
shuffle=True)
val_batch_size = 25
val_loader = torch.utils.data.DataLoader(val_data, batch_size=val_batch_size)
optimizer = torch.optim.Adam(model.parameters(), lr=1.e-3)
loss = torch.nn.NLLLoss()
loss.to(device)
tb_logger = torch.utils.tensorboard.SummaryWriter('runs/log_reg')
import sys
sys.path.append('src')
from logistic_regressor import LogisticRegressor
from matrix import Matrix
from dataframe import DataFrame
df = DataFrame.from_array([[1, 0.2], [2, 0.25], [3, 0.5]], columns=['x', 'y'])
log_reg = LogisticRegressor(df, 'y', 1)
print('Testing method predict...')
assert round(log_reg.predict({'x': 5}), 3) == 0.777
print('PASSED')
df = DataFrame.from_array(
[[0, 0, [], 1], [0, 0, ['mayo'], 1], [0, 0, ['jelly'], 4],
[0, 0, ['mayo', 'jelly'], 0.1], [5, 0, [], 4], [5, 0, ['mayo'], 8],
[5, 0, ['jelly'], 1], [5, 0, ['mayo', 'jelly'], 0.1], [0, 5, [], 5],
[0, 5, ['mayo'], 0.1], [0, 5, ['jelly'], 9],
[0, 5, ['mayo', 'jelly'], 0.1], [5, 5, [], 0.1], [5, 5, ['mayo'], 0.1],
[5, 5, ['jelly'], 0.1], [5, 5, ['mayo', 'jelly'], 0.1]],
columns=['beef', 'pb', 'condiments', 'rating'])
df = df.create_dummy_variables('condiments')
df = df.create_interaction_terms('beef', 'pb')
df = df.create_interaction_terms('beef', 'mayo')
df = df.create_interaction_terms('beef', 'jelly')
df = df.create_interaction_terms('pb', 'mayo')
df = df.create_interaction_terms('pb', 'jelly')
df = df.create_interaction_terms('mayo', 'jelly')
points = [[1, 0], [2, 0], [3, 0], [2, 1], [3, 1], [4, 1]]
df = DataFrame.from_array(points, ['x', 'y'])
def change_1s_0s_to(x, zero_val, one_val):
if x == 0:
return zero_val
elif x == 1:
return one_val
return x
df1 = df.apply('y', (lambda x: change_1s_0s_to(x, 0.1, 0.9)))
regressor1 = LogisticRegressor(df1, 'y', 1)
df2 = df.apply('y', (lambda x: change_1s_0s_to(x, 0.01, 0.99)))
regressor2 = LogisticRegressor(df2, 'y', 1)
df3 = df.apply('y', (lambda x: change_1s_0s_to(x, 0.001, 0.999)))
regressor3 = LogisticRegressor(df3, 'y', 1)
df4 = df.apply('y', (lambda x: change_1s_0s_to(x, 0.0001, 0.9999)))
regressor4 = LogisticRegressor(df4, 'y', 1)
plt.clf()
plt.style.use('bmh')
plt.plot([point[0] for point in points], [point[1] for point in points])
plt.plot([x / 1000 for x in range(5001)],
sys.path.append('src')
from matrix import Matrix
from dataframe import DataFrame
from linear_regressor import LinearRegressor
from logistic_regressor import LogisticRegressor
#test 1
Test_1 = False
if Test_1 == True:
df = DataFrame.from_array([[1, 0.2], [2, 0.25], [3, 0.5]],
columns=['x', 'y'])
log_reg = LogisticRegressor(df, dependent_variable='y')
assert round(log_reg.predict({'x': 5}), 3) == 0.777
