テキスト精神年齢分析(試作)

import nltk
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import numpy as np

# 必要なNLTKデータをダウンロード
nltk.download('punkt')

# サンプルデータ
texts = [
    "I love playing with my toys.", 
    "I am studying for my exams.", 
    "Retirement is just around the corner.",
    "I just got my first job.",  
    "I'm planning my vacation."
]
ages = [10, 20, 65, 25, 35]  # サンプルの精神年齢

# テキストをベクトル化
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)
y = np.array(ages)

# 訓練データとテストデータに分割
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)

# ロジスティック回帰モデルを訓練
model = LogisticRegression()
model.fit(X_train, y_train)

# 新しいテキストの精神年齢を予測する関数
def predict_age(text):
    text_vec = vectorizer.transform([text])
    predicted_age = model.predict(text_vec)
    return predicted_age[0]

# テスト
new_text = "I just started my first job."
predicted_age = predict_age(new_text)
print(f"The predicted mental age is: {predicted_age}")

!pip install nltk
!pip install sklearn