from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from data_preprocessing import getEcoliX, getEcoliY, getAdultX, getAdultY, getEcoliTestX, getEcoliTestY
import time
if __name__ == "__main__":
acc = {}
np.random.seed(0)
ecoliX = getEcoliX()
ecoliY = getEcoliY()
ecoliTestX = getEcoliTestX()
ecoliTestY = getEcoliTestY()
adultX = getAdultX()
adultX, adultTestX = adultX.iloc[:6000, :], adultX.iloc[6000:, :]
adultY = getAdultY()
adultY, adultTestY = adultY[:6000, ], adultY[6000:, ]
start_time = time.clock()
mlp = MLPClassifier(hidden_layer_sizes=(4, ),
learning_rate='constant',
learning_rate_init=0.2,
max_iter=500,
early_stopping=True,
random_state=5)
mlp.fit(ecoliX, ecoliY)
print("ecoli", time.clock() - start_time, "seconds")
acc['ecoli-train'] = accuracy_score(ecoliY, mlp.predict(ecoliX))
acc['ecoli-test'] = accuracy_score(ecoliTestY, mlp.predict(ecoliTestX))
start_time = time.clock()
from clustertesters import adult_KMeansTestCluster as kmtc
from data_preprocessing import getAdultX, getAdultY
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import numpy as np
if __name__ == "__main__":
X = getAdultX()
y = getAdultY()
tester = kmtc.KMeansTestCluster(X,
y,
clusters=range(1, 11),
plot=True,
targetcluster=2,
stats=True)
tester.run()
# plot clustering
kmeans = KMeans(n_clusters=3, max_iter=500, init='k-means++')
labels = kmeans.fit_predict(X)
# View the results
# Set the size of the plot
plt.figure(figsize=(14, 7))
# Create a colormap
colormap = np.array(['red', 'lime', 'black', 'blue', 'yellow'])
x1 = X.iloc[:, 0]
x2 = X.iloc[:, 1]
plt.scatter(x=x1, y=x2, c=colormap[labels], s=40)