Created
April 7, 2017 13:42
-
-
Save glemaitre/bc51bcd93b4bd4cc960734be9a41dfa2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
This is real case using the data of the Adult Census dataset available at: | |
https://archive.ics.uci.edu/ml/datasets/Adult | |
It will show that adding a smoothing noise do not has any influence on the | |
classification performance but allow for a better understanding when manually | |
checking the QuantileTransformer. | |
""" | |
import numpy as np | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
from sklearn.preprocessing import LabelEncoder | |
from sklearn.model_selection import train_test_split | |
from sklearn.preprocessing import QuantileTransformer | |
from sklearn.linear_model import LogisticRegression | |
from sklearn.pipeline import make_pipeline | |
N_QUANTILES = 1000 | |
usecols = (0, 2, 4, 10, 11, 12, 14) | |
data = pd.read_csv('adult.data', usecols=usecols) | |
X = data.iloc[:, :-1] | |
lc = LabelEncoder() | |
y = lc.fit_transform(data.iloc[:, -1]) | |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.33, | |
random_state=42) | |
pipeline_notrans = make_pipeline(LogisticRegression(random_state=0)) | |
pipeline_trans = make_pipeline( | |
QuantileTransformer(n_quantiles=N_QUANTILES, | |
output_distribution="uniform", | |
random_state=42), | |
LogisticRegression(random_state=0)) | |
pipeline_trans_noise = make_pipeline( | |
QuantileTransformer(n_quantiles=N_QUANTILES, | |
output_distribution="uniform", | |
smoothing_noise=1e-12, | |
random_state=42), | |
LogisticRegression(random_state=0)) | |
print('LR classification: score = {}'.format( | |
pipeline_notrans.fit(X_train, y_train).score(X_test, y_test))) | |
print('Transformer without smoothing noise + LR classification: ' | |
' score = {}'.format( | |
pipeline_trans.fit(X_train, y_train).score(X_test, y_test))) | |
print('Transformer with smoothing noise + LR classification: ' | |
' score = {}'.format( | |
pipeline_trans_noise.fit(X_train, y_train).score(X_test, y_test))) | |
qt_trans = pipeline_trans.named_steps['quantiletransformer'] | |
qt_trans_noise = pipeline_trans_noise.named_steps['quantiletransformer'] | |
f, axarr = plt.subplots(3, 2) | |
axarr = np.ravel(axarr) | |
for quantile, quantile_noise, ax in zip(qt_trans.quantiles_.T, | |
qt_trans_noise.quantiles_.T, | |
axarr): | |
c0 = ax.plot(quantile, np.linspace(0, 1, N_QUANTILES), | |
'b--', label='Without noise') | |
c1 = ax.plot(quantile_noise, np.linspace(0, 1, N_QUANTILES), | |
'r:', label='With noise') | |
# make nice plotting | |
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)) | |
ax.set_xlabel('Features value') | |
ax.set_ylabel('Associated quantiles') | |
ax.legend(loc="lower right") | |
plt.tight_layout() | |
# the features #6 --- numbers of hours per week --- seems to be a candidate to | |
# illustrate of using a smoothing noise to interpret some results | |
# create a typical feature to be transformed | |
X1 = np.reshape([50, 30000, 10, 10000, 2000, 40], (1, -1)) | |
X1t = qt_trans.transform(X1) | |
X1t_noise = qt_trans_noise.transform(X1) | |
fig = plt.figure() | |
ax = fig.add_subplot(1, 1, 1) | |
ax.plot(qt_trans.quantiles_.T[5], np.linspace(0, 1, num=N_QUANTILES)) | |
ax.scatter(X1[0, 5], X1t[0, 5], c='r', | |
label=r'Not smoothed -> $f({0}) = {1:.2f}$'.format(X1[0, 5], | |
X1t[0, 5])) | |
ax.scatter(X1[0, 5], X1t_noise[0, 5], c='g', | |
label=r'Smoothed -> $f({0}) = {1:.2f}$'.format(X1[0, 5], | |
X1t_noise[0, 5])) | |
# make nice plotting | |
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)) | |
ax.set_xlabel('Features value') | |
ax.set_ylabel('Associated quantiles') | |
ax.legend(loc="lower right") | |
ax.set_ylim([0, 1]) | |
ax.set_xlim([0, 100]) | |
ax.set_title('Number of hours worked per week') | |
plt.tight_layout() | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment