Pythonの練習

import pandas
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.linear_model import LinearRegression

nba = pandas.read_csv("nba_2013.csv")
print(nba.shape)
print(nba.head(1))
print(nba.mean())

sns.pairplot(nba[["ast", "fg", "trb"]])
plt.show()

kmeans_model = KMeans(n_clusters=5, random_state=1)
good_columns = nba._get_numeric_data().dropna(axis=1)
kmeans_model.fit(good_columns)
labels = kmeans_model.labels_

pca_2 = PCA(2)
plot_columns = pca_2.fit_transform(good_columns)
plt.scatter(x=plot_columns[:,0], y=plot_columns[:,1], c=labels)
plt.show()