full code.py

# Data preparation and import libraries

import pandas as pd
import numpy as np
import datetime as dt
# import matplotlib.pyplot as plt
# import seaborn as sns
import plotly.express as px

# %matplotlib inline

import warnings
warnings.filterwarnings('ignore')

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB

from sklearn.metrics import classification_report, accuracy_score
from sklearn.metrics import confusion_matrix

data = pd.read_csv('/kaggle/input/breast-cancer-wisconsin-data/data.csv')

# Data Exploration and Data Cleaning

data.head()

data.shape

data.info()

# Check Duplication
data.duplicated().sum()

# There aren't duplicate values

# check Missing value
data.isna().sum()

#- No Missing Value is avalible

# Check the number of unique values of each column
data.nunique()


#- Dropping the id and Unnamed: 32 columns which will not provide any information for our model
data = data.drop(['id','Unnamed: 32'], axis= 1)

#- Changed the name of the diagnostic column to target!
data = data.rename(columns={'diagnosis' : 'target'})

#- changed taget data in the dataset. I changed malignant to 1 and benign to 0.
data.target.replace({'M' : '1','B': '0'},inplace=True)

# Converting target type to int64
data.target = data.target.astype('float64')

### Data processing result
data.head()

data.tail()

data.info()

# Check statistic of dataset
data.describe().T


# Analysis📝 & EDA📊

# I looked at how many benign and malignant yields there are.
data.target.value_counts()

# visualized target data in the dataset.
data['target'].value_counts().plot(kind='bar',edgecolor='black',color=['lightsteelblue','navajowhite'])
plt.title(" Target",fontsize=20)
plt.show()

#- 1-->Malignant
#- 0-->Benign


# Correlation Analysis
cor = data.corr()
cor

plt.figure(figsize=(25,23))
sns.heatmap(cor, annot= True, linewidths= 0.3 ,linecolor = "black", fmt = ".2f")
plt.title('Correlation Heatmap')
plt.show()

#- Data with a correlation greater than 0.75.

threshold = 0.75
filtre = np.abs(cor["target"] > threshold)
corr_features = cor.columns[filtre].tolist()
plt.figure(figsize=(10,8))
sns.clustermap(data[corr_features].corr(), annot = True, fmt = ".2f")
plt.title("\n                               Correlation Between Features with Cor Thresgold [0.75]\n",fontsize=20)
plt.show()

###  visualized the data with a correlation greater than 0.75

sns.pairplot(data[corr_features], diag_kind = "kde" , markers = "*", hue="target")
plt.show()

# Machine Learning Model Evaluation

# Splitting data
x= data.drop('target',axis=1)
y= data['target']


x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.30,random_state=101)

s= StandardScaler()
x_train = s.fit_transform(x_train)
x_test = s.fit_transform(x_test)

algorithm = ['KNeighborsClassifier','RandomForestClassifier','DecisionTreeClassifier','GaussianNB','LogisticRegression']
Accuracy=[]

def all(model):
    model.fit(x_train,y_train)
    pred = model.predict(x_test)

    acc=accuracy_score(y_test,pred) 
    Accuracy.append(acc)

    # confusion matrix without Normalization
    print('confusion matrix')
    # Calculate confusion matrix
    cm = confusion_matrix(y_test,pred)
    # Plot the confusion matrix
    sns.heatmap(cm, annot=True, fmt='d',cmap=['lightsteelblue','navajowhite'])
    plt.title('Confusion matrix')
    plt.xlabel('Predcted lablel')
    plt.ylabel('True lable')
    plt.show()

    # confusion matrix without Normalization
    print('Normalized confusion matrix')
    # Calculate confusion matrix
    cm1 = confusion_matrix(y_test,pred, normalize='true')
    # Plot the confusion matrix
    sns.heatmap(cm1, annot=True,cmap=['lightsteelblue','navajowhite'])
    plt.title('Normalized Confusion  matrix')
    plt.xlabel('Predcted lablel')
    plt.ylabel('True lable')
    plt.show()

    # print Confusion matrix, Classification report and accuracy report
    print(cm)
    print(classification_report(y_test,pred))
    print('accuracy_score : ' , acc)
    

### KNN machine learning model Evaluation for breast cancer 

model_1 =KNeighborsClassifier(n_neighbors=2)
all(model_1)


### RandomForest
model_2= RandomForestClassifier(n_estimators=100,random_state=0)
all(model_2)

### DecisionTree

model_3 = DecisionTreeClassifier(random_state=42)
all(model_3)


### Naive_bayes
model_4 = GaussianNB()
all(model_4)

### Logistic Regression

model_5 = LogisticRegression()
all(model_5)

df = pd.DataFrame({'Algorithm':algorithm,'Accuracy':Accuracy })
df

fig = plt.figure(figsize=(20,10))
plt.plot(df.Algorithm,df.Accuracy,label='Accuracy',lw=5,color='peru',marker='o',markersize = 15)
plt.legend(fontsize=15)
plt.xlabel('\nModel',fontsize= 20)
plt.ylabel('Accuracy\n',fontsize= 20)
plt.show()