In [1]:

    

# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals

# Common imports
import numpy as np
import numpy.random as rnd
import os

# to make this notebook's output stable across runs
rnd.seed(42)

# To plot pretty figures
%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12

# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "training_linear_models"

def save_fig(fig_id, tight_layout=True):
    path = os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID, fig_id + ".png")
    print("Saving figure", fig_id)
    if tight_layout:
        plt.tight_layout()
    plt.savefig(path, format='png', dpi=300)


    

In [2]:

    

X = 2 * rnd.rand(100, 1)
y = 4 + 3 * X + rnd.randn(100, 1)


    

In [3]:

    

plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([0, 2, 0, 15])
save_fig("generated_data_plot")
plt.show()


    

    




Saving figure generated_data_plot






    

In [4]:

    

import numpy.linalg as LA

X_b = np.c_[np.ones((100, 1)), X]  # add x0 = 1 to each instance
theta_best = LA.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(y)


    

In [5]:

    

theta_best


    

    
Out[5]:





array([[ 4.21509616],
       [ 2.77011339]])

In [6]:

    

X_new = np.array([[0], [2]])
X_new_b = np.c_[np.ones((2, 1)), X_new]  # add x0 = 1 to each instance
y_predict = X_new_b.dot(theta_best)
y_predict


    

    
Out[6]:





array([[ 4.21509616],
       [ 9.75532293]])

In [7]:

    

plt.plot(X_new, y_predict, "r-", linewidth=2, label="Predictions")
plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.legend(loc="upper left", fontsize=14)
plt.axis([0, 2, 0, 15])
save_fig("linear_model_predictions")
plt.show()


    

    




Saving figure linear_model_predictions






    

In [8]:

    

from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
lin_reg.intercept_, lin_reg.coef_


    

    
Out[8]:





(array([ 4.21509616]), array([[ 2.77011339]]))

In [9]:

    

lin_reg.predict(X_new)


    

    
Out[9]:





array([[ 4.21509616],
       [ 9.75532293]])

In [10]:

    

theta_path_bgd = []

def plot_gradient_descent(theta, eta, theta_path=None):
    m = len(X_b)
    plt.plot(X, y, "b.")
    n_iterations = 1000
    for iteration in range(n_iterations):
        if iteration < 10:
            y_predict = X_new_b.dot(theta)
            style = "b-" if iteration > 0 else "r--"
            plt.plot(X_new, y_predict, style)
        gradients = 2/m * X_b.T.dot(X_b.dot(theta) - y)
        theta = theta - eta * gradients
        if theta_path is not None:
            theta_path.append(theta)
    plt.xlabel("$x_1$", fontsize=18)
    plt.axis([0, 2, 0, 15])
    plt.title(r"$\eta = {}$".format(eta), fontsize=16)

rnd.seed(42)
theta = rnd.randn(2,1)  # random initialization

plt.figure(figsize=(10,4))
plt.subplot(131); plot_gradient_descent(theta, eta=0.02)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.subplot(132); plot_gradient_descent(theta, eta=0.1, theta_path=theta_path_bgd)
plt.subplot(133); plot_gradient_descent(theta, eta=0.5)

save_fig("gradient_descent_plot")
plt.show()


    

    




Saving figure gradient_descent_plot






    

In [11]:

    

theta_path_sgd = []

n_iterations = 50
t0, t1 = 5, 50  # learning schedule hyperparameters

rnd.seed(42)
theta = rnd.randn(2,1)  # random initialization

def learning_schedule(t):
    return t0 / (t + t1)

m = len(X_b)

for epoch in range(n_iterations):
    for i in range(m):
        if epoch == 0 and i < 20:
            y_predict = X_new_b.dot(theta)
            style = "b-" if i > 0 else "r--"
            plt.plot(X_new, y_predict, style)
        random_index = rnd.randint(m)
        xi = X_b[random_index:random_index+1]
        yi = y[random_index:random_index+1]
        gradients = 2 * xi.T.dot(xi.dot(theta) - yi)
        eta = learning_schedule(epoch * m + i)
        theta = theta - eta * gradients
        theta_path_sgd.append(theta)

plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([0, 2, 0, 15])
save_fig("sgd_plot")
plt.show()


    

    




Saving figure sgd_plot






    

In [12]:

    

theta


    

    
Out[12]:





array([[ 4.21076011],
       [ 2.74856079]])

In [13]:

    

from sklearn.linear_model import SGDRegressor
sgd_reg = SGDRegressor(n_iter=50, penalty=None, eta0=0.1)
sgd_reg.fit(X, y.ravel())


    

    
Out[13]:





SGDRegressor(alpha=0.0001, average=False, epsilon=0.1, eta0=0.1,
       fit_intercept=True, l1_ratio=0.15, learning_rate='invscaling',
       loss='squared_loss', n_iter=50, penalty=None, power_t=0.25,
       random_state=None, shuffle=True, verbose=0, warm_start=False)

In [14]:

    

sgd_reg.intercept_, sgd_reg.coef_


    

    
Out[14]:





(array([ 4.23166744]), array([ 2.79099659]))

In [15]:

    

theta_path_mgd = []

n_iterations = 50
minibatch_size = 20

rnd.seed(42)
theta = rnd.randn(2,1)  # random initialization

t0, t1 = 10, 1000
def learning_schedule(t):
    return t0 / (t + t1)

t = 0
for epoch in range(n_iterations):
    shuffled_indices = rnd.permutation(m)
    X_b_shuffled = X_b[shuffled_indices]
    y_shuffled = y[shuffled_indices]
    for i in range(0, m, minibatch_size):
        t += 1
        xi = X_b_shuffled[i:i+minibatch_size]
        yi = y_shuffled[i:i+minibatch_size]
        gradients = 2 * xi.T.dot(xi.dot(theta) - yi)
        eta = learning_schedule(t)
        theta = theta - eta * gradients
        theta_path_mgd.append(theta)


    

In [16]:

    

theta


    

    
Out[16]:





array([[ 4.25214635],
       [ 2.7896408 ]])

In [17]:

    

theta_path_bgd = np.array(theta_path_bgd)
theta_path_sgd = np.array(theta_path_sgd)
theta_path_mgd = np.array(theta_path_mgd)


    

In [18]:

    

plt.figure(figsize=(7,4))
plt.plot(theta_path_sgd[:, 0], theta_path_sgd[:, 1], "r-s", linewidth=1, label="Stochastic")
plt.plot(theta_path_mgd[:, 0], theta_path_mgd[:, 1], "g-+", linewidth=2, label="Mini-batch")
plt.plot(theta_path_bgd[:, 0], theta_path_bgd[:, 1], "b-o", linewidth=3, label="Batch")
plt.legend(loc="upper left", fontsize=16)
plt.xlabel(r"$\theta_0$", fontsize=20)
plt.ylabel(r"$\theta_1$   ", fontsize=20, rotation=0)
plt.axis([2.5, 4.5, 2.3, 3.9])
save_fig("gradient_descent_paths_plot")
plt.show()


    

    




Saving figure gradient_descent_paths_plot






    

In [19]:

    

import numpy as np
import numpy.random as rnd

rnd.seed(42)
m = 100
X = 6 * rnd.rand(m, 1) - 3
y = 2 + X + 0.5 * X**2 + rnd.randn(m, 1)


    

In [20]:

    

plt.plot(X, y, "b.")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([-3, 3, 0, 10])
save_fig("quadratic_data_plot")
plt.show()


    

    




Saving figure quadratic_data_plot






    

In [21]:

    

from sklearn.preprocessing import PolynomialFeatures
poly_features = PolynomialFeatures(degree=2, include_bias=False)
X_poly = poly_features.fit_transform(X)
X[0]


    

    
Out[21]:





array([-0.75275929])

In [22]:

    

X_poly[0]


    

    
Out[22]:





array([-0.75275929,  0.56664654])

In [23]:

    

lin_reg = LinearRegression()
lin_reg.fit(X_poly, y)
lin_reg.intercept_, lin_reg.coef_


    

    
Out[23]:





(array([ 1.78134581]), array([[ 0.93366893,  0.56456263]]))

In [24]:

    

X_new=np.linspace(-3, 3, 100).reshape(100, 1)
X_new_poly = poly_features.transform(X_new)
y_new = lin_reg.predict(X_new_poly)
plt.plot(X, y, "b.")
plt.plot(X_new, y_new, "r-", linewidth=2, label="Predictions")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.legend(loc="upper left", fontsize=14)
plt.axis([-3, 3, 0, 10])
save_fig("quadratic_predictions_plot")
plt.show()


    

    




Saving figure quadratic_predictions_plot






    

In [25]:

    

from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

for style, width, degree in (("g-", 1, 300), ("b--", 2, 2), ("r-+", 2, 1)):
    polybig_features = PolynomialFeatures(degree=degree, include_bias=False)
    std_scaler = StandardScaler()
    lin_reg = LinearRegression()
    polynomial_regression = Pipeline((
            ("poly_features", polybig_features),
            ("std_scaler", std_scaler),
            ("lin_reg", lin_reg),
        ))
    polynomial_regression.fit(X, y)
    y_newbig = polynomial_regression.predict(X_new)
    plt.plot(X_new, y_newbig, style, label=str(degree), linewidth=width)

plt.plot(X, y, "b.", linewidth=3)
plt.legend(loc="upper left")
plt.xlabel("$x_1$", fontsize=18)
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.axis([-3, 3, 0, 10])
save_fig("high_degree_polynomials_plot")
plt.show()


    

    




Saving figure high_degree_polynomials_plot






    

In [26]:

    

from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split

def plot_learning_curves(model, X, y):
    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=10)
    train_errors, val_errors = [], []
    for m in range(1, len(X_train)):
        model.fit(X_train[:m], y_train[:m])
        y_train_predict = model.predict(X_train[:m])
        y_val_predict = model.predict(X_val)
        train_errors.append(mean_squared_error(y_train_predict, y_train[:m]))
        val_errors.append(mean_squared_error(y_val_predict, y_val))

    plt.plot(np.sqrt(train_errors), "r-+", linewidth=2, label="Training set")
    plt.plot(np.sqrt(val_errors), "b-", linewidth=3, label="Validation set")
    plt.legend(loc="upper right", fontsize=14)
    plt.xlabel("Training set size", fontsize=14)
    plt.ylabel("RMSE", fontsize=14)

lin_reg = LinearRegression()
plot_learning_curves(lin_reg, X, y)
plt.axis([0, 80, 0, 3])
save_fig("underfitting_learning_curves_plot")
plt.show()


    

    




Saving figure underfitting_learning_curves_plot






    

In [27]:

    

from sklearn.pipeline import Pipeline

polynomial_regression = Pipeline((
        ("poly_features", PolynomialFeatures(degree=10, include_bias=False)),
        ("sgd_reg", LinearRegression()),
    ))

plot_learning_curves(polynomial_regression, X, y)
plt.axis([0, 80, 0, 3])
save_fig("learning_curves_plot")
plt.show()


    

    




Saving figure learning_curves_plot






    

In [28]:

    

from sklearn.linear_model import Ridge

rnd.seed(42)
m = 20
X = 3 * rnd.rand(m, 1)
y = 1 + 0.5 * X + rnd.randn(m, 1) / 1.5
X_new = np.linspace(0, 3, 100).reshape(100, 1)

def plot_model(model_class, polynomial, alphas, **model_kargs):
    for alpha, style in zip(alphas, ("b-", "g--", "r:")):
        model = model_class(alpha, **model_kargs) if alpha > 0 else LinearRegression()
        if polynomial:
            model = Pipeline((
                    ("poly_features", PolynomialFeatures(degree=10, include_bias=False)),
                    ("std_scaler", StandardScaler()),
                    ("regul_reg", model),
                ))
        model.fit(X, y)
        y_new_regul = model.predict(X_new)
        lw = 2 if alpha > 0 else 1
        plt.plot(X_new, y_new_regul, style, linewidth=lw, label=r"$\alpha = {}$".format(alpha))
    plt.plot(X, y, "b.", linewidth=3)
    plt.legend(loc="upper left", fontsize=15)
    plt.xlabel("$x_1$", fontsize=18)
    plt.axis([0, 3, 0, 4])

plt.figure(figsize=(8,4))
plt.subplot(121)
plot_model(Ridge, polynomial=False, alphas=(0, 10, 100))
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.subplot(122)
plot_model(Ridge, polynomial=True, alphas=(0, 10**-5, 1))

save_fig("ridge_regression_plot")
plt.show()


    

    




Saving figure ridge_regression_plot






    

In [29]:

    

from sklearn.linear_model import Ridge
ridge_reg = Ridge(alpha=1, solver="cholesky")
ridge_reg.fit(X, y)
ridge_reg.predict([[1.5]])


    

    
Out[29]:





array([[ 1.55071465]])

In [30]:

    

sgd_reg = SGDRegressor(penalty="l2", random_state=42)
sgd_reg.fit(X, y.ravel())
sgd_reg.predict([[1.5]])


    

    
Out[30]:





array([ 1.13500145])

In [31]:

    

ridge_reg = Ridge(alpha=1, solver="sag")
ridge_reg.fit(X, y)
ridge_reg.predict([[1.5]])


    

    
Out[31]:





array([[ 1.55074549]])

In [32]:

    

from sklearn.linear_model import Lasso

plt.figure(figsize=(8,4))
plt.subplot(121)
plot_model(Lasso, polynomial=False, alphas=(0, 0.1, 1))
plt.ylabel("$y$", rotation=0, fontsize=18)
plt.subplot(122)
plot_model(Lasso, polynomial=True, alphas=(0, 10**-7, 1), tol=1)

save_fig("lasso_regression_plot")
plt.show()


    

    




Saving figure lasso_regression_plot






    

In [33]:

    

from sklearn.linear_model import Lasso
lasso_reg = Lasso(alpha=0.1)
lasso_reg.fit(X, y)
lasso_reg.predict([[1.5]])


    

    
Out[33]:





array([ 1.53788174])

In [34]:

    

from sklearn.linear_model import ElasticNet
elastic_net = ElasticNet(alpha=0.1, l1_ratio=0.5)
elastic_net.fit(X, y)
elastic_net.predict([[1.5]])


    

    
Out[34]:





array([ 1.54333232])

In [35]:

    

rnd.seed(42)
m = 100
X = 6 * rnd.rand(m, 1) - 3
y = 2 + X + 0.5 * X**2 + rnd.randn(m, 1)

X_train, X_val, y_train, y_val = train_test_split(X[:50], y[:50].ravel(), test_size=0.5, random_state=10)

poly_scaler = Pipeline((
        ("poly_features", PolynomialFeatures(degree=90, include_bias=False)),
        ("std_scaler", StandardScaler()),
    ))

X_train_poly_scaled = poly_scaler.fit_transform(X_train)
X_val_poly_scaled = poly_scaler.transform(X_val)

sgd_reg = SGDRegressor(n_iter=1,
                       penalty=None,
                       eta0=0.0005,
                       warm_start=True,
                       learning_rate="constant",
                       random_state=42)

n_epochs = 500
train_errors, val_errors = [], []
for epoch in range(n_epochs):
    sgd_reg.fit(X_train_poly_scaled, y_train)
    y_train_predict = sgd_reg.predict(X_train_poly_scaled)
    y_val_predict = sgd_reg.predict(X_val_poly_scaled)
    train_errors.append(mean_squared_error(y_train_predict, y_train))
    val_errors.append(mean_squared_error(y_val_predict, y_val))

best_epoch = np.argmin(val_errors)
best_val_rmse = np.sqrt(val_errors[best_epoch])

plt.annotate('Best model',
             xy=(best_epoch, best_val_rmse),
             xytext=(best_epoch, best_val_rmse + 1),
             ha="center",
             arrowprops=dict(facecolor='black', shrink=0.05),
             fontsize=16,
            )

best_val_rmse -= 0.03  # just to make the graph look better
plt.plot([0, n_epochs], [best_val_rmse, best_val_rmse], "k:", linewidth=2)
plt.plot(np.sqrt(val_errors), "b-", linewidth=3, label="Validation set")
plt.plot(np.sqrt(train_errors), "r--", linewidth=2, label="Training set")
plt.legend(loc="upper right", fontsize=14)
plt.xlabel("Epoch", fontsize=14)
plt.ylabel("RMSE", fontsize=14)
save_fig("early_stopping_plot")
plt.show()


    

    




Saving figure early_stopping_plot






    

In [36]:

    

from sklearn.base import clone
sgd_reg = SGDRegressor(n_iter=1, warm_start=True, penalty=None,
                       learning_rate="constant", eta0=0.0005,
                       random_state=42)

minimum_val_error = float("inf")
best_epoch = None
best_model = None
for epoch in range(1000):
    sgd_reg.fit(X_train_poly_scaled, y_train)  # continues where it left off
    y_val_predict = sgd_reg.predict(X_val_poly_scaled)
    val_error = mean_squared_error(y_val_predict, y_val)
    if val_error < minimum_val_error:
        minimum_val_error = val_error
        best_epoch = epoch
        best_model = clone(sgd_reg)

best_epoch, best_model


    

    
Out[36]:





(239, SGDRegressor(alpha=0.0001, average=False, epsilon=0.1, eta0=0.0005,
        fit_intercept=True, l1_ratio=0.15, learning_rate='constant',
        loss='squared_loss', n_iter=1, penalty=None, power_t=0.25,
        random_state=42, shuffle=True, verbose=0, warm_start=True))

In [37]:

    

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np


    

In [38]:

    

t1a, t1b, t2a, t2b = -1, 3, -1.5, 1.5

# ignoring bias term
t1s = np.linspace(t1a, t1b, 500)
t2s = np.linspace(t2a, t2b, 500)
t1, t2 = np.meshgrid(t1s, t2s)
T = np.c_[t1.ravel(), t2.ravel()]
Xr = np.array([[-1, 1], [-0.3, -1], [1, 0.1]])
yr = 2 * Xr[:, :1] + 0.5 * Xr[:, 1:]

J = (1/len(Xr) * np.sum((T.dot(Xr.T) - yr.T)**2, axis=1)).reshape(t1.shape)

N1 = np.linalg.norm(T, ord=1, axis=1).reshape(t1.shape)
N2 = np.linalg.norm(T, ord=2, axis=1).reshape(t1.shape)

t_min_idx = np.unravel_index(np.argmin(J), J.shape)
t1_min, t2_min = t1[t_min_idx], t2[t_min_idx]

t_init = np.array([[0.25], [-1]])


    

In [39]:

    

def bgd_path(theta, X, y, l1, l2, core = 1, eta = 0.1, n_iterations = 50):
    path = [theta]
    for iteration in range(n_iterations):
        gradients = core * 2/len(X) * X.T.dot(X.dot(theta) - y) + l1 * np.sign(theta) + 2 * l2 * theta

        theta = theta - eta * gradients
        path.append(theta)
    return np.array(path)

plt.figure(figsize=(12, 8))
for i, N, l1, l2, title in ((0, N1, 0.5, 0, "Lasso"), (1, N2, 0,  0.1, "Ridge")):
    JR = J + l1 * N1 + l2 * N2**2
    
    tr_min_idx = np.unravel_index(np.argmin(JR), JR.shape)
    t1r_min, t2r_min = t1[tr_min_idx], t2[tr_min_idx]

    levelsJ=(np.exp(np.linspace(0, 1, 20)) - 1) * (np.max(J) - np.min(J)) + np.min(J)
    levelsJR=(np.exp(np.linspace(0, 1, 20)) - 1) * (np.max(JR) - np.min(JR)) + np.min(JR)
    levelsN=np.linspace(0, np.max(N), 10)
    
    path_J = bgd_path(t_init, Xr, yr, l1=0, l2=0)
    path_JR = bgd_path(t_init, Xr, yr, l1, l2)
    path_N = bgd_path(t_init, Xr, yr, np.sign(l1)/3, np.sign(l2), core=0)

    plt.subplot(221 + i * 2)
    plt.grid(True)
    plt.axhline(y=0, color='k')
    plt.axvline(x=0, color='k')
    plt.contourf(t1, t2, J, levels=levelsJ, alpha=0.9)
    plt.contour(t1, t2, N, levels=levelsN)
    plt.plot(path_J[:, 0], path_J[:, 1], "w-o")
    plt.plot(path_N[:, 0], path_N[:, 1], "y-^")
    plt.plot(t1_min, t2_min, "rs")
    plt.title(r"$\ell_{}$ penalty".format(i + 1), fontsize=16)
    plt.axis([t1a, t1b, t2a, t2b])

    plt.subplot(222 + i * 2)
    plt.grid(True)
    plt.axhline(y=0, color='k')
    plt.axvline(x=0, color='k')
    plt.contourf(t1, t2, JR, levels=levelsJR, alpha=0.9)
    plt.plot(path_JR[:, 0], path_JR[:, 1], "w-o")
    plt.plot(t1r_min, t2r_min, "rs")
    plt.title(title, fontsize=16)
    plt.axis([t1a, t1b, t2a, t2b])

for subplot in (221, 223):
    plt.subplot(subplot)
    plt.ylabel(r"$\theta_2$", fontsize=20, rotation=0)

for subplot in (223, 224):
    plt.subplot(subplot)
    plt.xlabel(r"$\theta_1$", fontsize=20)

save_fig("lasso_vs_ridge_plot")
plt.show()


    

    




Saving figure lasso_vs_ridge_plot






    

In [40]:

    

t = np.linspace(-10, 10, 100)
sig = 1 / (1 + np.exp(-t))
plt.figure(figsize=(9, 3))
plt.plot([-10, 10], [0, 0], "k-")
plt.plot([-10, 10], [0.5, 0.5], "k:")
plt.plot([-10, 10], [1, 1], "k:")
plt.plot([0, 0], [-1.1, 1.1], "k-")
plt.plot(t, sig, "b-", linewidth=2, label=r"$\sigma(t) = \frac{1}{1 + e^{-t}}$")
plt.xlabel("t")
plt.legend(loc="upper left", fontsize=20)
plt.axis([-10, 10, -0.1, 1.1])
save_fig("logistic_function_plot")
plt.show()


    

    




Saving figure logistic_function_plot






    

In [41]:

    

from sklearn import datasets
iris = datasets.load_iris()
list(iris.keys())


    

    
Out[41]:





['target_names', 'DESCR', 'feature_names', 'target', 'data']

In [42]:

    

print(iris.DESCR)


    

    




Iris Plants Database
====================

Notes
-----
Data Set Characteristics:
    :Number of Instances: 150 (50 in each of three classes)
    :Number of Attributes: 4 numeric, predictive attributes and the class
    :Attribute Information:
        - sepal length in cm
        - sepal width in cm
        - petal length in cm
        - petal width in cm
        - class:
                - Iris-Setosa
                - Iris-Versicolour
                - Iris-Virginica
    :Summary Statistics:

    ============== ==== ==== ======= ===== ====================
                    Min  Max   Mean    SD   Class Correlation
    ============== ==== ==== ======= ===== ====================
    sepal length:   4.3  7.9   5.84   0.83    0.7826
    sepal width:    2.0  4.4   3.05   0.43   -0.4194
    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)
    petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)
    ============== ==== ==== ======= ===== ====================

    :Missing Attribute Values: None
    :Class Distribution: 33.3% for each of 3 classes.
    :Creator: R.A. Fisher
    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
    :Date: July, 1988

This is a copy of UCI ML iris datasets.
http://archive.ics.uci.edu/ml/datasets/Iris

The famous Iris database, first used by Sir R.A Fisher

This is perhaps the best known database to be found in the
pattern recognition literature.  Fisher's paper is a classic in the field and
is referenced frequently to this day.  (See Duda & Hart, for example.)  The
data set contains 3 classes of 50 instances each, where each class refers to a
type of iris plant.  One class is linearly separable from the other 2; the
latter are NOT linearly separable from each other.

References
----------
   - Fisher,R.A. "The use of multiple measurements in taxonomic problems"
     Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
     Mathematical Statistics" (John Wiley, NY, 1950).
   - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.
   - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
     Structure and Classification Rule for Recognition in Partially Exposed
     Environments".  IEEE Transactions on Pattern Analysis and Machine
     Intelligence, Vol. PAMI-2, No. 1, 67-71.
   - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE Transactions
     on Information Theory, May 1972, 431-433.
   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al"s AUTOCLASS II
     conceptual clustering system finds 3 classes in the data.
   - Many, many more ...

In [43]:

    

from sklearn.linear_model import LogisticRegression

X = iris["data"][:, 3:]  # petal width
y = (iris["target"] == 2).astype(np.int)  # 1 if Iris-Virginica, else 0

log_reg = LogisticRegression()
log_reg.fit(X, y)

X_new = np.linspace(0, 3, 1000).reshape(-1, 1)
y_proba = log_reg.predict_proba(X_new)
decision_boundary = X_new[y_proba[:, 1] >= 0.5][0]

plt.figure(figsize=(8, 3))
plt.plot(X[y==0], y[y==0], "bs")
plt.plot(X[y==1], y[y==1], "g^")
plt.plot([decision_boundary, decision_boundary], [-1, 2], "k:", linewidth=2)
plt.plot(X_new, y_proba[:, 1], "g-", linewidth=2, label="Iris-Virginica")
plt.plot(X_new, y_proba[:, 0], "b--", linewidth=2, label="Not Iris-Virginica")
plt.text(decision_boundary+0.02, 0.15, "Decision  boundary", fontsize=14, color="k", ha="center")
plt.arrow(decision_boundary, 0.08, -0.3, 0, head_width=0.05, head_length=0.1, fc='b', ec='b')
plt.arrow(decision_boundary, 0.92, 0.3, 0, head_width=0.05, head_length=0.1, fc='g', ec='g')
plt.xlabel("Petal width (cm)", fontsize=14)
plt.ylabel("Probability", fontsize=14)
plt.legend(loc="center left", fontsize=14)
plt.axis([0, 3, -0.02, 1.02])
save_fig("logistic_regression_plot")
plt.show()


    

    




Saving figure logistic_regression_plot






    

In [44]:

    

decision_boundary


    

    
Out[44]:





array([ 1.61561562])

In [45]:

    

log_reg.predict([[1.7], [1.5]])


    

    
Out[45]:





array([1, 0])

In [46]:

    

from sklearn.linear_model import LogisticRegression

X = iris["data"][:, (2, 3)]  # petal length, petal width
y = (iris["target"] == 2).astype(np.int)

log_reg = LogisticRegression(C=10**10)
log_reg.fit(X, y)

x0, x1 = np.meshgrid(
        np.linspace(2.9, 7, 500).reshape(-1, 1),
        np.linspace(0.8, 2.7, 200).reshape(-1, 1),
    )
X_new = np.c_[x0.ravel(), x1.ravel()]

y_proba = log_reg.predict_proba(X_new)

plt.figure(figsize=(10, 4))
plt.plot(X[y==0, 0], X[y==0, 1], "bs")
plt.plot(X[y==1, 0], X[y==1, 1], "g^")

zz = y_proba[:, 1].reshape(x0.shape)
contour = plt.contour(x0, x1, zz, cmap=plt.cm.brg)


left_right = np.array([2.9, 7])
boundary = -(log_reg.coef_[0][0] * left_right + log_reg.intercept_[0]) / log_reg.coef_[0][1]

plt.clabel(contour, inline=1, fontsize=12)
plt.plot(left_right, boundary, "k--", linewidth=3)
plt.text(3.5, 1.5, "Not Iris-Virginica", fontsize=14, color="b", ha="center")
plt.text(6.5, 2.3, "Iris-Virginica", fontsize=14, color="g", ha="center")
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.axis([2.9, 7, 0.8, 2.7])
save_fig("logistic_regression_contour_plot")
plt.show()


    

    




Saving figure logistic_regression_contour_plot






    

In [47]:

    

from sklearn.linear_model import LogisticRegression

X = iris["data"][:, (2, 3)]  # petal length, petal width
y = iris["target"]

softmax_reg = LogisticRegression(multi_class="multinomial", solver="lbfgs", C=10)
softmax_reg.fit(X, y)

x0, x1 = np.meshgrid(
        np.linspace(0, 8, 500).reshape(-1, 1),
        np.linspace(0, 3.5, 200).reshape(-1, 1),
    )
X_new = np.c_[x0.ravel(), x1.ravel()]


y_proba = softmax_reg.predict_proba(X_new)
y_predict = softmax_reg.predict(X_new)

zz1 = y_proba[:, 1].reshape(x0.shape)
zz = y_predict.reshape(x0.shape)

plt.figure(figsize=(10, 4))
plt.plot(X[y==2, 0], X[y==2, 1], "g^", label="Iris-Virginica")
plt.plot(X[y==1, 0], X[y==1, 1], "bs", label="Iris-Versicolor")
plt.plot(X[y==0, 0], X[y==0, 1], "yo", label="Iris-Setosa")

from matplotlib.colors import ListedColormap
custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])

plt.contourf(x0, x1, zz, cmap=custom_cmap, linewidth=5)
contour = plt.contour(x0, x1, zz1, cmap=plt.cm.brg)
plt.clabel(contour, inline=1, fontsize=12)
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.legend(loc="center left", fontsize=14)
plt.axis([0, 7, 0, 3.5])
save_fig("softmax_regression_contour_plot")
plt.show()


    

    




Saving figure softmax_regression_contour_plot






    

In [48]:

    

softmax_reg.predict([[5, 2]])


    

    
Out[48]:





array([2])

In [49]:

    

softmax_reg.predict_proba([[5, 2]])


    

    
Out[49]:





array([[  6.33134077e-07,   5.75276067e-02,   9.42471760e-01]])

In [ ]: