In [2]:
# %load ../common_import.py
import numpy as np
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt
from sklearn import datasets
In [3]:
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest
In [6]:
SVC?
In [14]:
iris = datasets.load_iris()
# X = pd.DataFrame(iris.data)
# y = pd.DataFrame(iris.target)
X, y = iris.data, iris.target
In [15]:
# This dataset is way too high-dimensional. Better do PCA:
pca = PCA(n_components=2)
# Maybe some original features where good, too?
selection = SelectKBest(k=1)
# Build estimator from PCA and Univariate selection:
combined_features = FeatureUnion([("pca", pca), ("univ_select", selection)])
# Use combined features to transform dataset:
X_features = combined_features.fit(X, y).transform(X)
svm =SVC(kernel="linear")
# Do grid search over k, n_components and C:
pipeline = Pipeline([("features", combined_features), ("svm", svm)])
param_grid = dict(features__pca__n_components=[1,2,3],
features__univ_select__k=[1, 2],
svm__C=[0.1, 1, 10])
In [16]:
grid_search = GridSearchCV(pipeline, param_grid=param_grid, verbose=10)
grid_search.fit(X, y)
print(grid_search.best_estimator_)
Fitting 3 folds for each of 18 candidates, totalling 54 fits
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1, score=0.9019607843137255, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=1, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=1, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=1, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=1, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=1, score=1.0, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1, score=0.9019607843137255, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=1, score=1.0, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2, score=0.9019607843137255, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=2, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=2, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=2, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=2, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2, score=1.0, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=2, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=2, score=1.0, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3, score=0.9803921568627451, total= 0.0s
[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 2 out of 2 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 3 out of 3 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 4 out of 4 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 5 out of 5 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 6 out of 6 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 7 out of 7 | elapsed: 0.0s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 8 out of 8 | elapsed: 0.1s remaining: 0.0s
[Parallel(n_jobs=1)]: Done 9 out of 9 | elapsed: 0.1s remaining: 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=0.1, features__pca__n_components=3, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3, score=1.0, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=1, features__pca__n_components=3, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3, score=1.0, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=1, svm__C=10, features__pca__n_components=3, score=1.0, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3, score=0.9803921568627451, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3, score=0.9411764705882353, total= 0.0s
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=0.1, features__pca__n_components=3, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3, score=1.0, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3, score=0.9607843137254902, total= 0.0s
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=1, features__pca__n_components=3, score=0.9791666666666666, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3, score=1.0, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3, score=0.9215686274509803, total= 0.0s
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3
[CV] features__univ_select__k=2, svm__C=10, features__pca__n_components=3, score=1.0, total= 0.0s
Pipeline(memory=None,
steps=[('features', FeatureUnion(n_jobs=1,
transformer_list=[('pca', PCA(copy=True, iterated_power='auto', n_components=2, random_state=None,
svd_solver='auto', tol=0.0, whiten=False)), ('univ_select', SelectKBest(k=2, score_func=<function f_classif at 0x11348c1e0>))],
transformer_we...,
max_iter=-1, probability=False, random_state=None, shrinking=True,
tol=0.001, verbose=False))])
[Parallel(n_jobs=1)]: Done 54 out of 54 | elapsed: 0.3s finished
In [ ]:
Content source: KECB/learn
Similar notebooks: