import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
import numpy as np

data_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data'
column_name = ['id', 'diagnosis', 'radius_mean', 'texture_mean', 'perimeter_mean', 'area_mean', 'smoothness_mean', 'compactness_mean', 'concavity_mean',
               'concave points_mean', 'symmetry_mean', 'fractal_dimension_mean', 'radius_se', 'texture_se', 'perimeter_se', 'area_se', 'smoothness_se',
               'compactness_se', 'concavity_se', 'concave points_se', 'symmetry_se', 'fractal_dimension_se', 'radius_worst', 'texture_worst', 'perimeter_worst',
               'area_worst', 'smoothness_worst', 'compactness_worst', 'concavity_worst', 'concave points_worst', 'symmetry_worst', 'fractal_dimension_worst']

df = pd.read_csv(data_url, names=column_name)
print(df.info())

X = df.loc[:, "radius_mean":].values
y = df.loc[:, "diagnosis"].values

le = LabelEncoder()
y = le.fit_transform(y)
print("종속변수 클래스:", le.classes_)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, stratify = y, random_state=1)

from sklearn.linear_model import LogisticRegression
pipe_lr = make_pipeline(StandardScaler(),
                        PCA(n_components=2),
                        LogisticRegression(solver="liblinear", random_state=1))

from sklearn.tree import DecisionTreeClassifier
pipe_lr = make_pipeline(StandardScaler(),
                        PCA(n_components=2),
                        DecisionTreeClassifier(random_state=0))

from lightgbm import LGBMClassifier
pipe_lr = make_pipeline(StandardScaler(),
                        PCA(n_components=2),
                        LGBMClassifier(objective='multiclass', random_state=5))

from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA

pipe_lr = make_pipeline(StandardScaler(),
                        PCA(n_components=2),
                        LogisticRegression(solver="liblinear", random_state=1))

kfold = StratifiedKFold(n_splits = 10, random_state=1, shuffle=True).split(X_train, y_train)
scores = []
for k, (train, test) in enumerate(kfold):
  pipe_lr.fit(X_train[train], y_train[train])
  score = pipe_lr.score(X_train[test], y_train[test])
  scores.append(score)
  print("폴드: %2d, 클래스 분포: %s, 정확도: %.3f" % (k+1, np.bincount(y_train[train]), score))

print("\nCV 정확도: %.3f +/- %.3f" % (np.mean(scores), np.std(scores)))

from sklearn.model_selection import cross_val_score
scores = cross_val_score(estimator=pipe_lr,
                         X = X_train,
                         y = y_train,
                         cv = 10,
                         n_jobs = 1)

print("CV 정확도 점수 : %s" % scores)
print("CV 정확도 : %.3f +/- %.3f" % (np.mean(scores), np.std(scores)))

import sklearn

print(cklearn.__version__)