Logistic regression -- case: cancer classification and prediction

Case study ： Cancer classification prediction - good ／ Prediction of malignant breast cancer

Data is introduced ：

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, roc_auc_score

# 1. get data 
names = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
                   'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin',
                   'Normal Nucleoli', 'Mitoses', 'Class']

data = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",
                  names=names)
# print(data.head())
# 2. Basic data processing 
# 2.1  Missing value processing 
data = data.replace(to_replace="?", value=np.nan)
data = data.dropna()

x = data.iloc[:, 1:-1]
# Remove target value 

print(x.head())

y = data["Class"]
print(y.head())


# 2.3  Split data 
x_train, x_test, y_train, y_test = train_test_split\
    (x, y, random_state=22, test_size=0.2)

# 3. Feature Engineering ( Standardization )
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)


# 4. machine learning ( Logical regression )
estimator = LogisticRegression()
estimator.fit(x_train, y_train)

# 5. Model to evaluate 
# 5.1  Accuracy rate 
ret = estimator.score(x_test, y_test)
print(" Accuracy rate is :\n", ret)

# 5.2  Predictive value 
y_pre = estimator.predict(x_test)
print(" Predictive value for :\n", y_pre)

# 5.3  Accuracy \ Recall index evaluation 
ret = classification_report(y_test, y_pre, labels=(2, 4), target_names=(" Benign ", " Malignant "))
print(ret)

# 5.4 auc Index calculation 
y_test = np.where(y_test>3, 1, 0)

print(roc_auc_score(y_test, y_pre))

Be careful ：

The difference between prediction call function and regression
Return to use mse, Mean square error

For classification score, Compare