sklearn tests

Sklearn/test4.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+from sklearn import set_config
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+from sklearn.impute import SimpleImputer
+from sklearn.compose import make_column_transformer
+from sklearn.linear_model import LogisticRegression
+set_config(display='diagram')
+
+num_proc = make_pipeline(SimpleImputer(strategy='median'), StandardScaler())
+
+cat_proc = make_pipeline(
+    SimpleImputer(strategy='constant', fill_value='missing'),
+    OneHotEncoder(handle_unknown='ignore'))
+
+preprocessor = make_column_transformer((num_proc, ('feat1', 'feat3')),
+                                       (cat_proc, ('feat0', 'feat2')))
+
+clf = make_pipeline(preprocessor, LogisticRegression())
+clf

Sklearn/test5.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+
+import numpy as np
+from matplotlib import pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.inspection import plot_partial_dependence
+from sklearn.experimental import enable_hist_gradient_boosting  # noqa
+from sklearn.ensemble import HistGradientBoostingRegressor
+
+n_samples = 500
+rng = np.random.RandomState(0)
+X = rng.randn(n_samples, 2)
+noise = rng.normal(loc=0.0, scale=0.01, size=n_samples)
+y = (5 * X[:, 0] + np.sin(10 * np.pi * X[:, 0]) - noise)
+
+gbdt_no_cst = HistGradientBoostingRegressor().fit(X, y)
+gbdt_cst = HistGradientBoostingRegressor(monotonic_cst=[1, 0]).fit(X, y)
+
+disp = plot_partial_dependence(
+    gbdt_no_cst, X, features=[0], feature_names=['feature 0'],
+    line_kw={'linewidth': 4, 'label': 'unconstrained'})
+plot_partial_dependence(gbdt_cst, X, features=[0],
+    line_kw={'linewidth': 4, 'label': 'constrained'}, ax=disp.axes_)
+disp.axes_[0, 0].plot(X[:, 0], y, 'o', alpha=.5, zorder=-1, label='samples')
+disp.axes_[0, 0].set_ylim(-3, 3); disp.axes_[0, 0].set_xlim(-1, 1)
+plt.legend()
+plt.show()

Sklearn/tuto.py

@@ -0,0 +1,16 @@
+#!/usr/bin/env python
+
+from sklearn import datasets
+from sklearn import svm
+iris = datasets.load_iris()
+digits = datasets.load_digits()
+
+# print(digits.data)
+# print(digits.target)
+# print(digits.images[0])
+
+from sklearn import svm
+clf = svm.SVC(gamma=0.001, C=100.)
+clf.fit(digits.data[:-1], digits.target[:-1])
+
+print(clf.predict(digits.data[-1:]))