def select_features(x, y):
"""
:param x: dataframe of features
:param y: dataframe of target property
:return: Outputs of feature selection process
"""
x = pd.DataFrame(x)
# Removing features with low variance
var_threshold = f_selection.VarianceThreshold(threshold=(.8 * (1 - .8)))
# Kbest-based and Percentile-based feature selection using regression
f_regress = f_selection.f_regression(x, y, center=False)
kbest = f_selection.SelectKBest(score_func=f_regress, k=2)
percent = f_selection.SelectPercentile(score_func=f_regress, percentile=10)
# Tree-based feature selection using a number of randomized decision trees
trees = f_selection.SelectFromModel(ExtraTreesRegressor, prefit=True)
# "False positive rate"-based feature selection using regression
fpr = f_selection.SelectFpr(score_func=f_regress, alpha=0.05)
# PCA-component evaluation
pca = PCA(n_components=2)
# Recursive feature elimination and cross-validated feature selection
estimator = SVR(kernel="linear")
selector = f_selection.RFECV(estimator, step=1, cv=5)
# Build estimator from PCA and Univariate selection:
combined_features = FeatureUnion([("pca_based", pca),
("univ_kbest", kbest),
("false_positive_rate", fpr),
("percentile_based", percent),
("RFECV_selector", selector),
("variance_threshold", var_threshold),
("trees_based", trees)])
x_union_features = combined_features.fit_transform(x, y)
svm = SVC(kernel="linear")
# Do grid search over all parameters:
pipeline = Pipeline([("features", x_union_features), ("svm", svm)])
grid = dict(features__pca_based__n_components=range(1, 101),
features__univ_kbest__k=range(1, 101),
features_false_positive_rate_alpha=range(0, 1, 0.01),
features_percentile_based_percentile=range(1, 20, 1),
features_RFECV_selector_cv=range(1, 5),
features_variance_threshold_threshold=range(0, 1, 0.01),
svm__C=[0.01, 0.1, 1.0, 10.0])
grid_search = GridSearchCV(pipeline, param_grid=grid, verbose=0)
x_features = grid_search.fit_transform(x, y)
# Pickling feature reduction outputs
with open(FS_PICKLE, 'wb') as result:
pickle.dump(rf_sorted_score, result, pickle.HIGHEST_PROTOCOL)
pickle.dump(grid_search.best_estimator_, result,
pickle.HIGHEST_PROTOCOL)
print grid_search.best_estimator_
return x_features
ax = fig.add_subplot(len(combos) / 2, 2, idx + 1, projection='3d')
ax.scatter(
pca_result[:,combo[0]]
, pca_result[:,combo[1]]
, pca_result[:,combo[2]]
, c=df.sval
, s=20
, cmap='YlOrRd' # red are the compounds with higher values of pIC50
)
ax.view_init(elev=30, azim=45)
ax.set_xlabel('PC%s' % (combo[0] + 1))
ax.set_ylabel('PC%s' % (combo[1] + 1))
ax.set_zlabel('PC%s' % (combo[2] + 1))
plt.show()
'''
from sklearn.manifold import TSNE
model = TSNE(n_components=2)
TSNEdata = model.fit_transform(df.iloc[:2000, 1:])
TSNEdf = pd.DataFrame(TSNEdata, columns=('x', 'y'))
TSNEdf['c'] = pd.Series(df.sval.values[:2000], index=TSNEdf.index)
plot = TSNEdf.plot.scatter(x='x', y='y', c='c', cmap='plasma')
plt.show()
