pca.py

import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler

import preprocessing

sns.set_style("darkgrid", {"axes.facecolor": ".95"})

breastcancer_data = preprocessing.get_data('breast-cancer-wisconsin.data')
data = preprocessing.process_missing_values(breastcancer_data, remove=False)
data = pd.DataFrame(data)
data.columns = breastcancer_data.columns

X = data[data.columns[:-1]].values
y = data[data.columns[-1]].values

X = StandardScaler().fit_transform(X)

pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)

X_pca_viz = pd.DataFrame(X_pca)
X_pca_viz.columns = ["comp1", "comp2"]
X_pca_viz['labels'] = y
sns.lmplot("comp1", "comp2", hue="labels", data=X_pca_viz, fit_reg=False)
plt.show()


"""tsne = TSNE()
X_tsne = tsne.fit_transform(X_pca)

plt.rcParams['figure.figsize'] = (10.0, 10.0)
proj = pd.DataFrame(X_tsne)
proj["labels"] = y
sns.lmplot("comp_1", "comp_2", hue="labels", data=proj.sample(5000), fit_reg=False)"""