def normalize_data_2d():
input_values, contaminated = ia_n2020.ioValues()
predict_values = ia_n2020.newData()
norm = StandardScaler()
input_values_norm = norm.fit_transform(input_values)
predict_values_norm = norm.fit_transform(predict_values)
pca = PCA(n_components=2)
input_values_2d = pca.fit_transform(input_values_norm)
predict_values_2d = pca.fit_transform(predict_values_norm)
reg1 = ''
reg2 = ''
for i in range(len(input_values_2d)):
if contaminated[i] == 0:
reg1 = plt.scatter(input_values_2d[i][0],
input_values_2d[i][1],
marker='x',
color='g')
elif contaminated[i] == 1:
reg2 = plt.scatter(input_values_2d[i][0],
input_values_2d[i][1],
marker='o',
color='b')
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.grid(True)
plt.legend((reg1, reg2), ('Não contaminado', 'Contaminado'))
plt.savefig('graphs/pca_graph.png')
plt.close()
return input_values_2d, predict_values_2d
def normalize_data_3d():
input_values, contaminated = ia_n2020.ioValues()
predict_values = ia_n2020.newData()
norm = StandardScaler()
input_values_norm = norm.fit_transform(input_values)
predict_values_norm = norm.fit_transform(predict_values)
pca = PCA(n_components=3)
input_values_3d = pca.fit_transform(input_values_norm)
predict_values_3d = pca.fit_transform(predict_values_norm)
return input_values_3d, predict_values_3d
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import ia_n2020
import pca_graph
import pandas as pd
input_values, contaminated = ia_n2020.ioValues()
input_values_2d, predict_values_2d = pca_graph.normalize_data_2d()
inertia = []
for i in range(1, 11):
kmeans = KMeans(n_clusters=i)
kmeans.fit(input_values_2d)
inertia.append(kmeans.inertia_)
plt.plot(inertia)
plt.xlabel('# Cluster - K')
plt.ylabel("Inertia")
plt.savefig('graphs/graph_kmeans_inertia')
plt.show()
kmeans_clf = KMeans(n_clusters=2)
kmeans_clf.fit(input_values_2d)
contaminated = kmeans_clf.predict(input_values_2d)
centroid = kmeans_clf.cluster_centers_
contaminated_predict = kmeans_clf.predict(predict_values_2d)
print(contaminated_predict)
spreadsheet = pd.read_csv('output_data/predict_data.csv')
spreadsheet['kmeans_predict'] = contaminated_predict
spreadsheet.to_csv('output_data/predict_data.csv', index=False)