import pandas as pd import numpy as np

df_data = pd.read_csv('/work/data.csv')

df_data.head(5)

df_data.isnull().sum()

df_data.info()

df_data.drop('Unnamed: 32', axis=1, inplace=True)

df_data.head(5)

df_data.drop('id', axis=1, inplace=True)

df_data['diagnosis'].replace(to_replace="B", value=1, inplace=True) df_data['diagnosis'].replace(to_replace="M", value=0, inplace=True)

df_data['diagnosis']

df_data_processing = df_data.copy()

import matplotlib.pyplot as plt

fig = plt.figure(figsize=(12,8)) df_data_processing.corr()['diagnosis'].sort_values(ascending=True).plot(kind='bar') plt.show()

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler() df_data_processing_scaled = scaler.fit_transform(df_data_processing)

df_data_processing_scaled = pd.DataFrame(df_data_processing_scaled)

df_data_processing_scaled.columns = df_data_processing.columns

df_data_processing_scaled.head(5)

X = df_data_processing_scaled.drop('diagnosis', axis=1) y = df_data_processing_scaled['diagnosis'].values

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.3, random_state=42)

from sklearn.linear_model import LogisticRegression model = LogisticRegression() result = model.fit(X_train, y_train)

from sklearn import metrics prediction_test = model.predict(X_test) print(metrics.accuracy_score(y_test, prediction_test))

model.predict_log_proba(X_test)

model.coef_

model.feature_names_in_

weights = pd.Series(model.coef_[0], index=X.columns.values) print(weights.sort_values(ascending=False)[:10].plot(kind='bar'))

print(weights.sort_values(ascending=False)[-10:].plot(kind='bar'))

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

fig = plt.figure(figsize=(11,11)) cm = confusion_matrix(y_test, prediction_test, labels=model.classes_) disp = ConfusionMatrixDisplay(confusion_matrix = cm, display_labels=model.classes_) disp.plot(cmap='gray') plt.show()