DataPreprocessing

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import KBinsDiscretizer
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.utils._testing import ignore_warnings
from sklearn.exceptions import ConvergenceWarning

print(__doc__)

h = .02  # step size in the mesh


def get_name(estimator):
    name = estimator.__class__.__name__
    if name == 'Pipeline':
        name = [get_name(est[1]) for est in estimator.steps]
        name = ' + '.join(name)
    return name


# list of (estimator, param_grid), where param_grid is used in GridSearchCV
classifiers = [
    (LogisticRegression(random_state=0), {
        'C': np.logspace(-2, 7, 10)
    }),
    (LinearSVC(random_state=0), {
        'C': np.logspace(-2, 7, 10)
    }),
    (make_pipeline(
        KBinsDiscretizer(encode='onehot'),
        LogisticRegression(random_state=0)), {
            'kbinsdiscretizer__n_bins': np.arange(2, 10),
            'logisticregression__C': np.logspace(-2, 7, 10),
        }),
    (make_pipeline(
        KBinsDiscretizer(encode='onehot'), LinearSVC(random_state=0)), {
            'kbinsdiscretizer__n_bins': np.arange(2, 10),
            'linearsvc__C': np.logspace(-2, 7, 10),
        }),
    (GradientBoostingClassifier(n_estimators=50, random_state=0), {
        'learning_rate': np.logspace(-4, 0, 10)
    }),
    (SVC(random_state=0), {
        'C': np.logspace(-2, 7, 10)
    }),
]

names = [get_name(e) for e, g in classifiers]

n_samples = 100
datasets = [
    make_moons(n_samples=n_samples, noise=0.2, random_state=0),
    make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),
    make_classification(n_samples=n_samples, n_features=2, n_redundant=0,
                        n_informative=2, random_state=2,
                        n_clusters_per_class=1)
]

fig, axes = plt.subplots(nrows=len(datasets), ncols=len(classifiers) + 1,
                         figsize=(21, 9))

cm = plt.cm.PiYG
cm_bright = ListedColormap(['#b30065', '#178000'])

# iterate over datasets
for ds_cnt, (X, y) in enumerate(datasets):
    print('\ndataset %d\n---------' % ds_cnt)

    # preprocess dataset, split into training and test part
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=.5, random_state=42)

    # create the grid for background colors
    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    xx, yy = np.meshgrid(
        np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))

    # plot the dataset first
    ax = axes[ds_cnt, 0]
    if ds_cnt == 0:
        ax.set_title("Input data")
    # plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
               edgecolors='k')
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,
               edgecolors='k')
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())

    # iterate over classifiers
    for est_idx, (name, (estimator, param_grid)) in \
            enumerate(zip(names, classifiers)):
        ax = axes[ds_cnt, est_idx + 1]

        clf = GridSearchCV(estimator=estimator, param_grid=param_grid)
        with ignore_warnings(category=ConvergenceWarning):
            clf.fit(X_train, y_train)
        score = clf.score(X_test, y_test)
        print('%s: %.2f' % (name, score))

        # plot the decision boundary. For that, we will assign a color to each
        # point in the mesh [x_min, x_max]*[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
        else:
            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # plot the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
                   edgecolors='k')
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
                   edgecolors='k', alpha=0.6)
        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())

        if ds_cnt == 0:
            ax.set_title(name.replace(' + ', '\n'))
        ax.text(0.95, 0.06, ('%.2f' % score).lstrip('0'), size=15,
                bbox=dict(boxstyle='round', alpha=0.8, facecolor='white'),
                transform=ax.transAxes, horizontalalignment='right')

plt.tight_layout()
# Add suptitles above the figure
plt.subplots_adjust(top=0.90)
suptitles = [
    'Linear classifiers',
    'Feature discretization and linear classifiers',
    'Non-linear classifiers',
]
for i, suptitle in zip([1, 3, 5], suptitles):
    ax = axes[0, i]
    ax.text(1.05, 1.25, suptitle, transform=ax.transAxes,
            horizontalalignment='center', size='x-large')
plt.show()

import numpy as np
import matplotlib.pyplot as plt

from sklearn.preprocessing import PowerTransformer
from sklearn.preprocessing import QuantileTransformer
from sklearn.model_selection import train_test_split

print(__doc__)


N_SAMPLES = 1000
FONT_SIZE = 6
BINS = 30


rng = np.random.RandomState(304)
bc = PowerTransformer(method='box-cox')
yj = PowerTransformer(method='yeo-johnson')
# n_quantiles is set to the training set size rather than the default value
# to avoid a warning being raised by this example
qt = QuantileTransformer(n_quantiles=500, output_distribution='normal',
                         random_state=rng)
size = (N_SAMPLES, 1)


# lognormal distribution
X_lognormal = rng.lognormal(size=size)

# chi-squared distribution
df = 3
X_chisq = rng.chisquare(df=df, size=size)

# weibull distribution
a = 50
X_weibull = rng.weibull(a=a, size=size)

# gaussian distribution
loc = 100
X_gaussian = rng.normal(loc=loc, size=size)

# uniform distribution
X_uniform = rng.uniform(low=0, high=1, size=size)

# bimodal distribution
loc_a, loc_b = 100, 105
X_a, X_b = rng.normal(loc=loc_a, size=size), rng.normal(loc=loc_b, size=size)
X_bimodal = np.concatenate([X_a, X_b], axis=0)


# create plots
distributions = [
    ('Lognormal', X_lognormal),
    ('Chi-squared', X_chisq),
    ('Weibull', X_weibull),
    ('Gaussian', X_gaussian),
    ('Uniform', X_uniform),
    ('Bimodal', X_bimodal)
]

colors = ['#D81B60', '#0188FF', '#FFC107',
          '#B7A2FF', '#000000', '#2EC5AC']

fig, axes = plt.subplots(nrows=8, ncols=3, figsize=plt.figaspect(2))
axes = axes.flatten()
axes_idxs = [(0, 3, 6, 9), (1, 4, 7, 10), (2, 5, 8, 11), (12, 15, 18, 21),
             (13, 16, 19, 22), (14, 17, 20, 23)]
axes_list = [(axes[i], axes[j], axes[k], axes[l])
             for (i, j, k, l) in axes_idxs]


for distribution, color, axes in zip(distributions, colors, axes_list):
    name, X = distribution
    X_train, X_test = train_test_split(X, test_size=.5)

    # perform power transforms and quantile transform
    X_trans_bc = bc.fit(X_train).transform(X_test)
    lmbda_bc = round(bc.lambdas_[0], 2)
    X_trans_yj = yj.fit(X_train).transform(X_test)
    lmbda_yj = round(yj.lambdas_[0], 2)
    X_trans_qt = qt.fit(X_train).transform(X_test)

    ax_original, ax_bc, ax_yj, ax_qt = axes

    ax_original.hist(X_train, color=color, bins=BINS)
    ax_original.set_title(name, fontsize=FONT_SIZE)
    ax_original.tick_params(axis='both', which='major', labelsize=FONT_SIZE)

    for ax, X_trans, meth_name, lmbda in zip(
            (ax_bc, ax_yj, ax_qt),
            (X_trans_bc, X_trans_yj, X_trans_qt),
            ('Box-Cox', 'Yeo-Johnson', 'Quantile transform'),
            (lmbda_bc, lmbda_yj, None)):
        ax.hist(X_trans, color=color, bins=BINS)
        title = 'After {}'.format(meth_name)
        if lmbda is not None:
            title += '\n$\\lambda$ = {}'.format(lmbda)
        ax.set_title(title, fontsize=FONT_SIZE)
        ax.tick_params(axis='both', which='major', labelsize=FONT_SIZE)
        ax.set_xlim([-3.5, 3.5])
plt.tight_layout()
plt.show()

fig, (ax1, ax2) = plt.subplots(ncols=2, sharey=True, figsize=(10, 4))
line = np.linspace(-3, 3, 1000, endpoint=False).reshape(-1, 1)
reg = LinearRegression().fit(X, y)
ax1.plot(line, reg.predict(line), linewidth=2, color='green',
         label="linear regression")
reg = DecisionTreeRegressor(min_samples_split=3, random_state=0).fit(X, y)
ax1.plot(line, reg.predict(line), linewidth=2, color='red',
         label="decision tree")
ax1.plot(X[:, 0], y, 'o', c='k')
ax1.legend(loc="best")
ax1.set_ylabel("Regression output")
ax1.set_xlabel("Input feature")
ax1.set_title("Result before discretization")

# predict with transformed dataset
line_binned = enc.transform(line)
reg = LinearRegression().fit(X_binned, y)
ax2.plot(line, reg.predict(line_binned), linewidth=2, color='green',
         linestyle='-', label='linear regression')
reg = DecisionTreeRegressor(min_samples_split=3,
                            random_state=0).fit(X_binned, y)
ax2.plot(line, reg.predict(line_binned), linewidth=2, color='red',
         linestyle=':', label='decision tree')
ax2.plot(X[:, 0], y, 'o', c='k')
ax2.vlines(enc.bin_edges_[0], *plt.gca().get_ylim(), linewidth=1, alpha=.2)
ax2.legend(loc="best")
ax2.set_xlabel("Input feature")
ax2.set_title("Result after discretization")

plt.tight_layout()
plt.show()

import numpy as np
import matplotlib.pyplot as plt

from sklearn.preprocessing import KBinsDiscretizer
from sklearn.datasets import make_blobs

print(__doc__)

strategies = ['uniform', 'quantile', 'kmeans']

n_samples = 200
centers_0 = np.array([[0, 0], [0, 5], [2, 4], [8, 8]])
centers_1 = np.array([[0, 0], [3, 1]])

# construct the datasets
random_state = 42
X_list = [
    np.random.RandomState(random_state).uniform(-3, 3, size=(n_samples, 2)),
    make_blobs(n_samples=[n_samples // 10, n_samples * 4 // 10,
                          n_samples // 10, n_samples * 4 // 10],
               cluster_std=0.5, centers=centers_0,
               random_state=random_state)[0],
    make_blobs(n_samples=[n_samples // 5, n_samples * 4 // 5],
               cluster_std=0.5, centers=centers_1,
               random_state=random_state)[0],
]

figure = plt.figure(figsize=(14, 9))
i = 1
for ds_cnt, X in enumerate(X_list):

    ax = plt.subplot(len(X_list), len(strategies) + 1, i)
    ax.scatter(X[:, 0], X[:, 1], edgecolors='k')
    if ds_cnt == 0:
        ax.set_title("Input data", size=14)

    xx, yy = np.meshgrid(
        np.linspace(X[:, 0].min(), X[:, 0].max(), 300),
        np.linspace(X[:, 1].min(), X[:, 1].max(), 300))
    grid = np.c_[xx.ravel(), yy.ravel()]

    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())

    i += 1
    # transform the dataset with KBinsDiscretizer
    for strategy in strategies:
        enc = KBinsDiscretizer(n_bins=4, encode='ordinal', strategy=strategy)
        enc.fit(X)
        grid_encoded = enc.transform(grid)

        ax = plt.subplot(len(X_list), len(strategies) + 1, i)

        # horizontal stripes
        horizontal = grid_encoded[:, 0].reshape(xx.shape)
        ax.contourf(xx, yy, horizontal, alpha=.5)
        # vertical stripes
        vertical = grid_encoded[:, 1].reshape(xx.shape)
        ax.contourf(xx, yy, vertical, alpha=.5)

        ax.scatter(X[:, 0], X[:, 1], edgecolors='k')
        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        if ds_cnt == 0:
            ax.set_title("strategy='%s'" % (strategy, ), size=14)

        i += 1

plt.tight_layout()
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.naive_bayes import GaussianNB
from sklearn import metrics
import matplotlib.pyplot as plt
from sklearn.datasets import load_wine
from sklearn.pipeline import make_pipeline
print(__doc__)

# Code source: Tyler Lanigan <tylerlanigan@gmail.com>
#              Sebastian Raschka <mail@sebastianraschka.com>

# License: BSD 3 clause

RANDOM_STATE = 42
FIG_SIZE = (10, 7)


features, target = load_wine(return_X_y=True)

# Make a train/test split using 30% test size
X_train, X_test, y_train, y_test = train_test_split(features, target,
                                                    test_size=0.30,
                                                    random_state=RANDOM_STATE)

# Fit to data and predict using pipelined GNB and PCA.
unscaled_clf = make_pipeline(PCA(n_components=2), GaussianNB())
unscaled_clf.fit(X_train, y_train)
pred_test = unscaled_clf.predict(X_test)

# Fit to data and predict using pipelined scaling, GNB and PCA.
std_clf = make_pipeline(StandardScaler(), PCA(n_components=2), GaussianNB())
std_clf.fit(X_train, y_train)
pred_test_std = std_clf.predict(X_test)

# Show prediction accuracies in scaled and unscaled data.
print('\nPrediction accuracy for the normal test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test)))

print('\nPrediction accuracy for the standardized test dataset with PCA')
print('{:.2%}\n'.format(metrics.accuracy_score(y_test, pred_test_std)))

# Extract PCA from pipeline
pca = unscaled_clf.named_steps['pca']
pca_std = std_clf.named_steps['pca']

# Show first principal components
print('\nPC 1 without scaling:\n', pca.components_[0])
print('\nPC 1 with scaling:\n', pca_std.components_[0])

# Use PCA without and with scale on X_train data for visualization.
X_train_transformed = pca.transform(X_train)
scaler = std_clf.named_steps['standardscaler']
X_train_std_transformed = pca_std.transform(scaler.transform(X_train))

# visualize standardized vs. untouched dataset with PCA performed
fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=FIG_SIZE)


for l, c, m in zip(range(0, 3), ('blue', 'red', 'green'), ('^', 's', 'o')):
    ax1.scatter(X_train_transformed[y_train == l, 0],
                X_train_transformed[y_train == l, 1],
                color=c,
                label='class %s' % l,
                alpha=0.5,
                marker=m
                )

for l, c, m in zip(range(0, 3), ('blue', 'red', 'green'), ('^', 's', 'o')):
    ax2.scatter(X_train_std_transformed[y_train == l, 0],
                X_train_std_transformed[y_train == l, 1],
                color=c,
                label='class %s' % l,
                alpha=0.5,
                marker=m
                )

ax1.set_title('Training dataset after PCA')
ax2.set_title('Standardized training dataset after PCA')

for ax in (ax1, ax2):
    ax.set_xlabel('1st principal component')
    ax.set_ylabel('2nd principal component')
    ax.legend(loc='upper right')
    ax.grid()

plt.tight_layout()

plt.show()

import numpy as np

import matplotlib as mpl
from matplotlib import pyplot as plt
from matplotlib import cm

from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import minmax_scale
from sklearn.preprocessing import MaxAbsScaler
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import RobustScaler
from sklearn.preprocessing import Normalizer
from sklearn.preprocessing import QuantileTransformer
from sklearn.preprocessing import PowerTransformer

from sklearn.datasets import fetch_california_housing

print(__doc__)

dataset = fetch_california_housing()
X_full, y_full = dataset.data, dataset.target

# Take only 2 features to make visualization easier
# Feature of 0 has a long tail distribution.
# Feature 5 has a few but very large outliers.

X = X_full[:, [0, 5]]

distributions = [
    ('Unscaled data', X),
    ('Data after standard scaling',
        StandardScaler().fit_transform(X)),
    ('Data after min-max scaling',
        MinMaxScaler().fit_transform(X)),
    ('Data after max-abs scaling',
        MaxAbsScaler().fit_transform(X)),
    ('Data after robust scaling',
        RobustScaler(quantile_range=(25, 75)).fit_transform(X)),
    ('Data after power transformation (Yeo-Johnson)',
     PowerTransformer(method='yeo-johnson').fit_transform(X)),
    ('Data after power transformation (Box-Cox)',
     PowerTransformer(method='box-cox').fit_transform(X)),
    ('Data after quantile transformation (uniform pdf)',
        QuantileTransformer(output_distribution='uniform')
        .fit_transform(X)),
    ('Data after quantile transformation (gaussian pdf)',
        QuantileTransformer(output_distribution='normal')
        .fit_transform(X)),
    ('Data after sample-wise L2 normalizing',
        Normalizer().fit_transform(X)),
]

# scale the output between 0 and 1 for the colorbar
y = minmax_scale(y_full)

# plasma does not exist in matplotlib < 1.5
cmap = getattr(cm, 'plasma_r', cm.hot_r)

def create_axes(title, figsize=(16, 6)):
    fig = plt.figure(figsize=figsize)
    fig.suptitle(title)

    # define the axis for the first plot
    left, width = 0.1, 0.22
    bottom, height = 0.1, 0.7
    bottom_h = height + 0.15
    left_h = left + width + 0.02

    rect_scatter = [left, bottom, width, height]
    rect_histx = [left, bottom_h, width, 0.1]
    rect_histy = [left_h, bottom, 0.05, height]

    ax_scatter = plt.axes(rect_scatter)
    ax_histx = plt.axes(rect_histx)
    ax_histy = plt.axes(rect_histy)

    # define the axis for the zoomed-in plot
    left = width + left + 0.2
    left_h = left + width + 0.02

    rect_scatter = [left, bottom, width, height]
    rect_histx = [left, bottom_h, width, 0.1]
    rect_histy = [left_h, bottom, 0.05, height]

    ax_scatter_zoom = plt.axes(rect_scatter)
    ax_histx_zoom = plt.axes(rect_histx)
    ax_histy_zoom = plt.axes(rect_histy)

    # define the axis for the colorbar
    left, width = width + left + 0.13, 0.01

    rect_colorbar = [left, bottom, width, height]
    ax_colorbar = plt.axes(rect_colorbar)

    return ((ax_scatter, ax_histy, ax_histx),
            (ax_scatter_zoom, ax_histy_zoom, ax_histx_zoom),
            ax_colorbar)


def plot_distribution(axes, X, y, hist_nbins=50, title="",
                      x0_label="", x1_label=""):
    ax, hist_X1, hist_X0 = axes

    ax.set_title(title)
    ax.set_xlabel(x0_label)
    ax.set_ylabel(x1_label)

    # The scatter plot
    colors = cmap(y)
    ax.scatter(X[:, 0], X[:, 1], alpha=0.5, marker='o', s=5, lw=0, c=colors)

    # Removing the top and the right spine for aesthetics
    # make nice axis layout
    ax.spines['top'].set_visible(False)
    ax.spines['right'].set_visible(False)
    ax.get_xaxis().tick_bottom()
    ax.get_yaxis().tick_left()
    ax.spines['left'].set_position(('outward', 10))
    ax.spines['bottom'].set_position(('outward', 10))

    # Histogram for axis X1 (feature 5)
    hist_X1.set_ylim(ax.get_ylim())
    hist_X1.hist(X[:, 1], bins=hist_nbins, orientation='horizontal',
                 color='grey', ec='grey')
    hist_X1.axis('off')

    # Histogram for axis X0 (feature 0)
    hist_X0.set_xlim(ax.get_xlim())
    hist_X0.hist(X[:, 0], bins=hist_nbins, orientation='vertical',
                 color='grey', ec='grey')
    hist_X0.axis('off')
# 不同的scale 处理效果
def make_plot(item_idx):
    title, X = distributions[item_idx]
    ax_zoom_out, ax_zoom_in, ax_colorbar = create_axes(title)
    axarr = (ax_zoom_out, ax_zoom_in)
    plot_distribution(axarr[0], X, y, hist_nbins=200,
                      x0_label="Median Income",
                      x1_label="Number of households",
                      title="Full data")

    # zoom-in
    zoom_in_percentile_range = (0, 99)
    cutoffs_X0 = np.percentile(X[:, 0], zoom_in_percentile_range)
    cutoffs_X1 = np.percentile(X[:, 1], zoom_in_percentile_range)

    non_outliers_mask = (
        np.all(X > [cutoffs_X0[0], cutoffs_X1[0]], axis=1) &
        np.all(X < [cutoffs_X0[1], cutoffs_X1[1]], axis=1))
    plot_distribution(axarr[1], X[non_outliers_mask], y[non_outliers_mask],
                      hist_nbins=50,
                      x0_label="Median Income",
                      x1_label="Number of households",
                      title="Zoom-in")

    norm = mpl.colors.Normalize(y_full.min(), y_full.max())
    mpl.colorbar.ColorbarBase(ax_colorbar, cmap=cmap,
                              norm=norm, orientation='vertical',
                              label='Color mapping for values of y')