hash encoding complete code

## Importing Libraries
import pandas as pd
from category_encoders import HashingEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.ensemble import RandomForestClassifier


## Importing Dataset
columns=['class','age','menopause','tumor_size','inv_nodes','node_caps','deg_malig','breast','breast_quad','irradiat']
df=pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer/breast-cancer.data",names=columns)


## Data Processing
df['class']=df['class'].apply(lambda x: 0 if x=='no-recurrence-events' else 1)
categorical_data=df.select_dtypes(include=['object'])
df_he=df.copy()


## Encoding
for column_name in categorical_data.columns  :
    unique_components=len(categorical_data[column_name].unique())
    hashencoder=HashingEncoder(cols=column_name,n_components=unique_components)
    transformed_data=hashencoder.fit_transform(df_he[column_name])
    temp_col=transformed_data.columns  
    transformed_data.columns=[column_name + col for col in temp_col]
    df_he[transformed_data.columns  ] = transformed_data


## Splitting Dataset
df_he=df_he.drop(columns=categorical_data.columns)
y=df_he.pop('class')
X_train, X_test, y_train, y_test = train_test_split(df_he, y, test_size=0.1, random_state=42)


## Model Implementation
clf = RandomForestClassifier()
clf = clf.fit(X_train, y_train)
predictions=clf.predict(X_test)
print(classification_report(predictions,y_test))