【Streamlit】AutoML入門：機械学習自動化の実装ガイド

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# データ準備
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.3, random_state=42
)

# 複数モデル定義
models = {
    "Decision Tree": DecisionTreeClassifier(),
    "Random Forest": RandomForestClassifier(),
    "Logistic Regression": LogisticRegression(max_iter=200)
}

# 各モデルの学習・評価
results = {}
for name, model in models.items():
    model.fit(X_train, y_train)
    preds = model.predict(X_test)
    acc = accuracy_score(y_test, preds)
    results[name] = acc

print(results)

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# データ準備
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.3, random_state=42
)

# 複数モデル定義
models = {
    "Decision Tree": DecisionTreeClassifier(),
    "Random Forest": RandomForestClassifier(),
    "Logistic Regression": LogisticRegression(max_iter=200)
}

# 各モデルの学習・評価
results = {}
for name, model in models.items():
    model.fit(X_train, y_train)
    preds = model.predict(X_test)
    acc = accuracy_score(y_test, preds)
    results[name] = acc

print(results)

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import RandomizedSearchCV


# データ準備
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.3, random_state=42
)

param_dist = {
    "n_estimators": [10, 50, 100, 200],
    "max_depth": [None, 5, 10, 20],
}

rf = RandomForestClassifier(random_state=42)
random_search = RandomizedSearchCV(
    rf, param_distributions=param_dist, n_iter=5, cv=3, random_state=42
)
random_search.fit(X_train, y_train)
print("Best params:", random_search.best_params_)
print("Best score:", random_search.best_score_)

RandomizedSearchCV(
    estimator,          # モデル（例: RandomForestClassifierなど）
    param_distributions, # 探索するパラメータとその分布
    n_iter=10,           # 試行回数
    scoring=None,        # 評価指標（例: "accuracy", "neg_mean_squared_error"など）
    cv=None,             # クロスバリデーション分割数（例: 5）
    random_state=None,   # 乱数シード（再現性確保）
    verbose=0,           # ログ出力の詳細度
    n_jobs=None          # 並列処理数（-1で全CPU使用）
)

import streamlit as st
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# データ準備
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.3, random_state=42
)

# Streamlit UI設定
st.title("簡単AutoMLデモ")

model_name = st.sidebar.selectbox(
    "モデルを選択してください",
    ("Decision Tree", "Random Forest", "Logistic Regression")
)

if model_name == "Decision Tree":
    max_depth = st.sidebar.slider("最大深さ (max_depth)", 1, 20, 5)
    model = DecisionTreeClassifier(max_depth=max_depth)
elif model_name == "Random Forest":
    n_estimators = st.sidebar.slider("木の数 (n_estimators)", 10, 200, 100)
    model = RandomForestClassifier(n_estimators=n_estimators)
else:
    max_iter = st.sidebar.slider("最大反復回数 (max_iter)", 50, 300, 200)
    model = LogisticRegression(max_iter=max_iter)

# モデル学習
model.fit(X_train, y_train)
preds = model.predict(X_test)
acc = accuracy_score(y_test, preds)

st.write(f"選択モデル: **{model_name}**")
st.write(f"モデルの精度（Accuracy）: **{acc:.4f}**")

import time
import pandas as pd

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# データ準備
data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.3, random_state=42
)


models = {
    "Decision Tree": DecisionTreeClassifier(max_depth=5),
    "Random Forest": RandomForestClassifier(n_estimators=100),
    "Logistic Regression": LogisticRegression(max_iter=200),
}

results = []

for name, model in models.items():
    start_train = time.time()
    model.fit(X_train, y_train)
    train_time = time.time() - start_train

    start_pred = time.time()
    preds = model.predict(X_test)
    pred_time = time.time() - start_pred

    acc = accuracy_score(y_test, preds)
    results.append({
        "Model": name,
        "Accuracy": acc,
        "Training Time (s)": train_time,
        "Prediction Time (s)": pred_time
    })

df_results = pd.DataFrame(results)
print(df_results)