def scale_data(train_data, test_data):
Z_train, y_train = zip(*train_data)
scale = Scaler()
scale.fit(Z_train)
transform = compose(prepend_x0, scale.transform)
scaledX_train = transform(Z_train)
scaled_train = list(zip(scaledX_train, y_train))
Z_test, y_test = zip(*test_data)
scaledX_test = transform(Z_test)
scaled_test = list(zip(scaledX_test, y_test))
return scaled_train, scaled_test
def _common(self, Z, y):
scale = Scaler(Z)
transform = compose(prepend_x0, Scaler.normalize)
X = transform(scale)
data = zip(X, y)
h_theta0 = [0.] * len(X[0])
coeff = compose(scale.denormalize, get(0),
lin_reg(J, gradJ, h_theta0, it_max=2000))
h_thetad = coeff(data)
return h_thetad
import glm
import metrics
from utility import Scaler
from ml_util import train_test_split
from out_utils import plot_cost, plot_errors
# Get the data
input = np.loadtxt('./data/Folds.csv', delimiter=',', skiprows=1)
Z = np.array(list(pluck(list(range(0, len(input[0])-1)), input)))
y = np.array(list(pluck(len(input[0])-1, input)))
data = zip(Z, y)
# Split into a train set and test set
train_data, test_data = train_test_split(data, 0.33)
# Scale the training data
scale = Scaler()
Z_train, y_train = zip(*train_data)
scale.fit(Z_train)
X_train = scale.transform(Z_train)
scaledtrain_data = list(zip(X_train, y_train))
# Scale the testing data using the same scaling parameters
# used for the training data
Z_test, y_test = zip(*test_data)
X_test = scale.transform(Z_test)
print('****Minibatch Gradient Descent****')
print('\n--Training--\n')
hyperparam = {'eta': 0.3,
'epochs': 300,
'minibatches': 1,
'adaptive': 0.99}
Z, q = csv_reader('./data/iris.csv', ['SL', 'SW', 'PL', 'PW'], 'Type')
# Get Sepal Length and Petal Length features
Zp = list(pluck([0, 2], Z))
# Get only the Iris Setosa (0) and Iris Versicolour (1) classes
datap = [[f, o] for f, o in zip(Zp, q) if o != 2.0]
Xp, yp = zip(*datap)
y = list(yp)
Xpp = [list(e) for e in Xp]
print(Xpp)
print(y)
# Split set into training and testing data
train_data, test_data = train_test_split(zip(Xpp, y), 0.33)
# Scale the data
X_train, y_train = zip(*train_data)
scale = Scaler()
scale.fit(X_train)
transform = compose(prepend_x0, scale.transform)
scaledX_train = transform(X_train)
scaled_train = zip(scaledX_train, y_train)
# Fit the training data
h_theta0 = [1., 1., 1.]
print('****Gradient Descent****\n')
print('--Training--\n')
h_thetaf, cost = glm.fit(logr.logistic_log_likelihood,
logr.grad_logistic,
h_theta0,
scaled_train,
eta=0.03,
it_max=500,
gf='gd')
from tabulate import tabulate
from utility import csv_reader, Scaler, prepend_x0
import metrics
import linear_regression as lr
import glm
from ml_util import train_test_split
import numpy as np
from numpy.linalg import lstsq
# Get the data
Z, y = csv_reader('./data/Folds_small.csv', ['AT', 'V', 'AP', 'RH'], 'PE')
data = zip(Z, y)
# Split into a train set and test set
train_data, test_data = train_test_split(data, 0.33)
# Scale the training data
scale = Scaler()
Z_train, y_train = zip(*train_data)
scale.fit(Z_train)
transform = compose(prepend_x0, scale.transform)
X_train = transform(Z_train)
scaledtrain_data = zip(X_train, y_train)
# Scale the testing data using the same scaling parameters
# used for the training data
Z_test, y_test = zip(*test_data)
X_test = transform(Z_test)
h_theta0 = [0., 0., 0., 0., 0.]
print('****Gradient Descent****')
h_thetaf, cost = glm.fit(lr.J,
lr.gradJ,
h_theta0,
# Get the iris data set
# SL: sepal length, SW: Sepal Width, PL: Petal Length, PW: Petal Width
# 0: Iris Setosa 1: Iris Versicolour 2: Iris Virginica
Z, q = csv_reader('./data/iris.csv', ['SL', 'SW', 'PL', 'PW'], 'Type')
t = list(zip(Z, q))
random.shuffle(t)
W, u = list(zip(*t))
yencoded = encode_labels(np.array(u), 3)
train_data, test_data = train_test_split(zip(W, yencoded), 0.33)
# Scale data
Z_train, y_train = zip(*train_data)
y_train = np.array(y_train)
scale = Scaler()
scale.fit(Z_train)
scaledX_train = scale.transform(Z_train)
Z_test, y_test = zip(*test_data)
y_test = np.array(y_test)
scaledX_test = scale.transform(Z_test)
hyperparam = {'eta': 0.5,
'epochs': 1000,
'minibatches': 4,
'adaptive': 0.98}
weightsf, cost = glm.fit(lr.SMC,
lr.gradSMC,
hyperparam,
zip(scaledX_train, y_train))
from utility import Scaler, prepend_x0
from out_utils import logistic_table
import metrics
data = [(0.7,48000,1),(1.9,48000,0),(2.5,60000,1),(4.2,63000,0),(6,76000,0),(6.5,69000,0),(7.5,76000,0),(8.1,88000,0),(8.7,83000,1),(10,83000,1),(0.8,43000,0),(1.8,60000,0),(10,79000,1),(6.1,76000,0),(1.4,50000,0),(9.1,92000,0),(5.8,75000,0),(5.2,69000,0),(1,56000,0),(6,67000,0),(4.9,74000,0),(6.4,63000,1),(6.2,82000,0),(3.3,58000,0),(9.3,90000,1),(5.5,57000,1),(9.1,102000,0),(2.4,54000,0),(8.2,65000,1),(5.3,82000,0),(9.8,107000,0),(1.8,64000,0),(0.6,46000,1),(0.8,48000,0),(8.6,84000,1),(0.6,45000,0),(0.5,30000,1),(7.3,89000,0),(2.5,48000,1),(5.6,76000,0),(7.4,77000,0),(2.7,56000,0),(0.7,48000,0),(1.2,42000,0),(0.2,32000,1),(4.7,56000,1),(2.8,44000,1),(7.6,78000,0),(1.1,63000,0),(8,79000,1),(2.7,56000,0),(6,52000,1),(4.6,56000,0),(2.5,51000,0),(5.7,71000,0),(2.9,65000,0),(1.1,33000,1),(3,62000,0),(4,71000,0),(2.4,61000,0),(7.5,75000,0),(9.7,81000,1),(3.2,62000,0),(7.9,88000,0),(4.7,44000,1),(2.5,55000,0),(1.6,41000,0),(6.7,64000,1),(6.9,66000,1),(7.9,78000,1),(8.1,102000,0),(5.3,48000,1),(8.5,66000,1),(0.2,56000,0),(6,69000,0),(7.5,77000,0),(8,86000,0),(4.4,68000,0),(4.9,75000,0),(1.5,60000,0),(2.2,50000,0),(3.4,49000,1),(4.2,70000,0),(7.7,98000,0),(8.2,85000,0),(5.4,88000,0),(0.1,46000,0),(1.5,37000,0),(6.3,86000,0),(3.7,57000,0),(8.4,85000,0),(2,42000,0),(5.8,69000,1),(2.7,64000,0),(3.1,63000,0),(1.9,48000,0),(10,72000,1),(0.2,45000,0),(8.6,95000,0),(1.5,64000,0),(9.8,95000,0),(5.3,65000,0),(7.5,80000,0),(9.9,91000,0),(9.7,50000,1),(2.8,68000,0),(3.6,58000,0),(3.9,74000,0),(4.4,76000,0),(2.5,49000,0),(7.2,81000,0),(5.2,60000,1),(2.4,62000,0),(8.9,94000,0),(2.4,63000,0),(6.8,69000,1),(6.5,77000,0),(7,86000,0),(9.4,94000,0),(7.8,72000,1),(0.2,53000,0),(10,97000,0),(5.5,65000,0),(7.7,71000,1),(8.1,66000,1),(9.8,91000,0),(8,84000,0),(2.7,55000,0),(2.8,62000,0),(9.4,79000,0),(2.5,57000,0),(7.4,70000,1),(2.1,47000,0),(5.3,62000,1),(6.3,79000,0),(6.8,58000,1),(5.7,80000,0),(2.2,61000,0),(4.8,62000,0),(3.7,64000,0),(4.1,85000,0),(2.3,51000,0),(3.5,58000,0),(0.9,43000,0),(0.9,54000,0),(4.5,74000,0),(6.5,55000,1),(4.1,41000,1),(7.1,73000,0),(1.1,66000,0),(9.1,81000,1),(8,69000,1),(7.3,72000,1),(3.3,50000,0),(3.9,58000,0),(2.6,49000,0),(1.6,78000,0),(0.7,56000,0),(2.1,36000,1),(7.5,90000,0),(4.8,59000,1),(8.9,95000,0),(6.2,72000,0),(6.3,63000,0),(9.1,100000,0),(7.3,61000,1),(5.6,74000,0),(0.5,66000,0),(1.1,59000,0),(5.1,61000,0),(6.2,70000,0),(6.6,56000,1),(6.3,76000,0),(6.5,78000,0),(5.1,59000,0),(9.5,74000,1),(4.5,64000,0),(2,54000,0),(1,52000,0),(4,69000,0),(6.5,76000,0),(3,60000,0),(4.5,63000,0),(7.8,70000,0),(3.9,60000,1),(0.8,51000,0),(4.2,78000,0),(1.1,54000,0),(6.2,60000,0),(2.9,59000,0),(2.1,52000,0),(8.2,87000,0),(4.8,73000,0),(2.2,42000,1),(9.1,98000,0),(6.5,84000,0),(6.9,73000,0),(5.1,72000,0),(9.1,69000,1),(9.8,79000,1),]
data = map(list, data) # change tuples to lists
# each element is [experience, salary]
Z = [row[:2] for row in data]
# each element is paid_account
y = [row[2] for row in data]
massaged_data = zip(Z, y)
train_data, test_data = train_test_split(massaged_data, 0.33)
Z_train, y_train = zip(*train_data)
scale = Scaler()
scale.fit(Z_train)
transform = compose(prepend_x0, scale.transform)
scaledX_train = transform(Z_train)
scaled_train = zip(scaledX_train, y_train)
Z_test, y_test = zip(*test_data)
scaledX_test = transform(Z_test)
scaled_test = zip(scaledX_test, y_test)
print('****Gradient Descent****\n')
h_theta0 = [1., 1., 1.]
h_thetaf, cost = glm.fit(logr.logistic_log_likelihood,
logr.grad_logistic,
h_theta0,
scaled_train,
eta=0.1,
it_max=1000,
Z, q = csv_reader('./data/iris.csv', ['SL', 'SW', 'PL', 'PW'], 'Type')
# Get Sepal Length and Petal Length features
Zp = list(pluck([0, 2], Z))
# Get only the Iris Setosa (0) and Iris Versicolour (1) classes
datap = [[f, o] for f, o in zip(Zp, q) if o != 2.0]
Xp, yp = zip(*datap)
y = list(yp)
Xpp = [list(e) for e in Xp]
print(Xpp)
print(y)
# Split set into training and testing data
train_data, test_data = train_test_split(zip(Xpp, y), 0.33)
# Scale the data
X_train, y_train = zip(*train_data)
scale = Scaler()
scale.fit(X_train)
transform = compose(prepend_x0, scale.transform)
scaledX_train = transform(X_train)
scaled_train = zip(scaledX_train, y_train)
# Fit the training data
h_theta0 = [1., 1., 1.]
print('****Gradient Descent****\n')
print('--Training--\n')
h_thetaf, cost = glm.fit(logr.logistic_log_likelihood,
logr.grad_logistic,
h_theta0,
scaled_train,
eta=0.03,
it_max=500,
gf='gd')