दिन 36: Machine Learning क्या है?

import pandas as pd
loans = pd.read_csv("loan_applications.csv")
print(loans.head())
rule = (loans["monthly_income"] > 40000) & (loans["credit_score"] > 700)
print(f"Old rule accuracy: {(rule.astype(int) == loans['approved']).mean():.1%}")
print(f"Approval rate in history: {loans['approved'].mean():.1%}")

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
loans = pd.read_csv("loan_applications.csv")
X = loans[["monthly_income", "credit_score", "loan_amount", "years_employed"]]
y = loans["approved"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42, stratify=y)
model = DecisionTreeClassifier(max_depth=4, random_state=42).fit(X_train, y_train)
print(f"ML model accuracy on unseen applications: {model.score(X_test, y_test):.1%}")

import pandas as pd
h = pd.read_csv("house_prices.csv")
X = h.drop(columns="price_lakh")      # features (inputs)
y = h["price_lakh"]                   # label / target (what we predict)
print("Features:", list(X.columns))
print("Target:", y.name, "| one example →", dict(X.iloc[0]), "→", y.iloc[0], "lakh")

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
loans = pd.read_csv("loan_applications.csv")
X = loans[["monthly_income", "credit_score", "loan_amount", "years_employed"]]; y = loans["approved"]
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.25, random_state=42, stratify=y)
for depth in [1, 2, 4, 8, 16, None]:
    m = DecisionTreeClassifier(max_depth=depth, random_state=42).fit(X_tr, y_tr)
    print(f"depth={str(depth):4s} train={m.score(X_tr, y_tr):.3f}  test={m.score(X_te, y_te):.3f}")

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
loans = pd.read_csv("loan_applications.csv")
X = loans[["monthly_income", "credit_score", "loan_amount", "years_employed"]]; y = loans["approved"]
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.25, random_state=42, stratify=y)
d = range(1, 16); tr, te = [], []
for k in d:
    m = DecisionTreeClassifier(max_depth=k, random_state=42).fit(X_tr, y_tr)
    tr.append(m.score(X_tr, y_tr)); te.append(m.score(X_te, y_te))
plt.figure(figsize=(8.5, 3.8))
plt.plot(d, tr, marker="o", label="training accuracy", color="#94a3b8")
plt.plot(d, te, marker="o", label="test accuracy", color="#4f46e5")
best = d[te.index(max(te))]; plt.axvline(best, color="#16a34a", ls="--", label=f"sweet spot (depth {best})")
plt.xlabel("model complexity (tree depth)"); plt.ylabel("accuracy"); plt.legend()
plt.title("Too simple = underfit, too complex = overfit"); plt.show()