Шаблон классификации ⇐ Python

[Anonymous]

Что вы думаете об этом шаблоне классификации

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.metrics import accuracy_score

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier

# Load data
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")

# Set target column
target_col = "target" # change this
id_cols = [col for col in ["id", "ID"] if col in train.columns]

# Features and target
X = train.drop(columns=[target_col] + id_cols, errors="ignore")
y = train[target_col]
X_test = test.drop(columns=id_cols, errors="ignore")

# Column types
numeric_features = X.select_dtypes(include=["int64", "float64"]).columns
categorical_features = X.select_dtypes(include=["object", "category", "bool"]).columns

# Preprocessing
numeric_transformer = Pipeline(steps=[
("imputer", SimpleImputer(strategy="median")),
("scaler", StandardScaler())
])

categorical_transformer = Pipeline(steps=[
("imputer", SimpleImputer(strategy="most_frequent")),
("onehot", OneHotEncoder(handle_unknown="ignore"))
])

preprocessor = ColumnTransformer(transformers=[
("num", numeric_transformer, numeric_features),
("cat", categorical_transformer, categorical_features)
])

# Split
X_train, X_val, y_train, y_val = train_test_split(
X, y, test_size=0.2, random_state=42, stratify=y
)

# Models
models = {
"logreg": LogisticRegression(max_iter=1000),
"rf": RandomForestClassifier(random_state=42),
"knn": KNeighborsClassifier(),
"dt": DecisionTreeClassifier(random_state=42)
}

best_model = None
best_score = -1
best_name = None

for name, clf in models.items():
pipeline = Pipeline(steps=[
("preprocessor", preprocessor),
("model", clf)
])

pipeline.fit(X_train, y_train)
pred_val = pipeline.predict(X_val)
acc = accuracy_score(y_val, pred_val)
print(name, acc)

if acc > best_score:
best_score = acc
best_model = pipeline
best_name = name

print("Best model:", best_name, best_score)

# Retrain on full data
best_model.fit(X, y)
test_pred = best_model.predict(X_test)

# Save submission
submission = pd.DataFrame(test_pred, columns=[target_col])
submission.to_csv("submission.csv", index=False)
print("Saved submission.csv")