Feature Engineering و Pipelines

import pandas as pd

df = pd.DataFrame({"city": ["Cairo", "Giza", "Alexandria", "Cairo"]})
print(pd.get_dummies(df, columns=["city"], dtype=int))

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error

df = pd.read_csv("apartments.csv")
numeric = ["area", "rooms", "floor", "age", "metro_km"]
categorical = ["city"]

X_train, X_test, y_train, y_test = train_test_split(
    df[numeric + categorical], df["price_k"], test_size=0.2, random_state=42)

prep = ColumnTransformer([
    ("num", StandardScaler(), numeric),                          # scale numbers
    ("cat", OneHotEncoder(handle_unknown="ignore"), categorical), # encode text
])
pipe = Pipeline([("prep", prep), ("model", LinearRegression())])

pipe.fit(X_train, y_train)
mae = mean_absolute_error(y_test, pipe.predict(X_test))
print(f"MAE with city: {mae:.0f}K EGP")

import joblib
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression

df = pd.read_csv("apartments.csv")
cols = ["area", "rooms", "floor", "age", "metro_km", "city"]
pipe = Pipeline([
    ("prep", ColumnTransformer([("cat", OneHotEncoder(), ["city"])],
                               remainder="passthrough")),
    ("model", LinearRegression()),
]).fit(df[cols], df["price_k"])

joblib.dump(pipe, "price_model.joblib")        # save to disk

loaded = joblib.load("price_model.joblib")     # later, in another program
flat = pd.DataFrame([{"area": 130, "rooms": 3, "floor": 4, "age": 5,
                      "metro_km": 1.2, "city": "Cairo"}])
print(f"Cairo flat: {loaded.predict(flat)[0]:,.0f}K EGP")