یک راهنمای گام به گام برای چرخه عمر پروژه علوم داده

import pandas as pd  
df = pd.read_csv("dataset.csv")  
print(df.info())  

df.fillna(df.mean(), inplace=True)  # Handle missing values  
df = pd.get_dummies(df, drop_first=True)  # Convert categorical data  

from sklearn.model_selection import train_test_split  
from sklearn.ensemble import RandomForestClassifier  

X_train, X_test, y_train, y_test = train_test_split(df.drop("target", axis=1), df["target"], test_size=0.2)  
model = RandomForestClassifier().fit(X_train, y_train)