books/books.dewey/learn.py

# Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

# Sample data (replace it with your actual dataset)
data = {
    'Amount': [100, 50, 200, 150, 75],
    'Merchant': ['StoreA', 'StoreB', 'StoreA', 'StoreC', 'StoreB'],
    'Date': ['2022-01-01', '2022-01-02', '2022-01-03', '2022-01-04', '2022-01-05'],
    'TransactionType': ['Bensin', 'Matur', 'Bensin', 'Rafmagn', 'Matur']
}

df = pd.DataFrame(data)

# Preprocessing and Feature Engineering
le_merchant = LabelEncoder()
df['Merchant'] = le_merchant.fit_transform(df['Merchant'])

df['Date'] = pd.to_datetime(df['Date'])
df['DayOfWeek'] = df['Date'].dt.dayofweek
df['IsWeekend'] = df['DayOfWeek'].isin([5, 6]).astype(int)

# Drop unnecessary columns
df = df.drop(['Date', 'DayOfWeek'], axis=1)

# Define features and target variable
X = df.drop('TransactionType', axis=1)
y = df['TransactionType']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train a RandomForestClassifier (replace with your preferred model)
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')

# Display classification report
print('Classification Report:')
print(classification_report(y_test, y_pred))