import sys
sys.path.append("E:/utils")
import classification_utils as cutils
from sklearn import preprocessing
import numpy as np
X, y = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=1000,
noise=0.1)
X, y = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=1000,
noise=0.1)
cutils.plot_data_2d_classification(X, y)
#guassian basis transformation
tmp = np.exp(-(X**2).sum(1))
X_3d = np.c_[X, tmp]
cutils.plot_data_3d_classification(
X_3d,
y,
new_window=True,
title="Linearly separable data in 3D with basis change")
#polynomial basis transformation
poly_features = preprocessing.PolynomialFeatures()
X_poly1 = poly_features.fit_transform(X)
poly_features = preprocessing.PolynomialFeatures(degree=3)
X_poly2 = poly_features.fit_transform(X)
import sys
path = 'J://utils'
sys.path.append(path)
from sklearn import cluster, manifold
import common_utils as utils
import clustering_utils as cl_utils
import classification_utils as cutils
X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)
utils.plot_data_2d(X)
X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)
utils.plot_data_2d(X)
tsne = manifold.TSNE()
X_tsne = tsne.fit_transform(X)
utils.plot_data_2d(X_tsne)
scoring = 's_score'
kmeans_estimator = cluster.KMeans()
kmeans_grid = {'n_clusters': list(range(2, 7))}
kmeans_final_model = cl_utils.grid_search_best_model_clustering(
kmeans_estimator, kmeans_grid, X, scoring=scoring)
print(kmeans_final_model.labels_)
print(kmeans_final_model.cluster_centers_)
cl_utils.plot_model_2d_clustering(kmeans_final_model, X)
import sys
sys.path.append("E:/")
import classification_utils as cutils
from sklearn import model_selection, neighbors, metrics
import numpy as np
X_train, y_train = cutils.generate_nonlinear_synthetic_data_classification3(
n_samples=500, noise=0.25)
cutils.plot_data_2d_classification(X_train, y_train)
#underfitted learning in knn
knn_estimator = neighbors.KNeighborsClassifier(n_neighbors=400)
knn_estimator.fit(X_train, y_train)
cv_scores = model_selection.cross_val_score(knn_estimator,
X_train,
y_train,
cv=10)
print(np.mean(cv_scores))
train_score = knn_estimator.score(X_train, y_train)
print(train_score)
cutils.plot_model_2d_classification(knn_estimator, X_train, y_train)
#underfitted learning in knn
knn_estimator = neighbors.KNeighborsClassifier(n_neighbors=1)
knn_estimator.fit(X_train, y_train)
cv_scores = model_selection.cross_val_score(knn_estimator,
X_train,
y_train,
cv=10)
print(np.mean(cv_scores))