Scikit-learnのTF-IDFでメンタルヘルス資源の推奨システムを構築する

pip install pandas scikit-learn

id,type,title,description
1,Meditation,"5-Minute Mindfulness Meditation","A short guided meditation to bring awareness to the present moment. Ideal for beginners looking to reduce stress and improve focus. Helps calm an anxious mind and find peace in your day. mindfulness, stress, anxiety, focus"
2,Breathing Exercise,"Box Breathing for Anxiety","A simple and powerful breathing technique to calm your nervous system. Inhale for 4 counts, hold for 4, exhale for 4, and hold for 4. Excellent for immediate anxiety and stress relief. anxiety, stress, calm, breathing"
3,Article,"How to Manage Workplace Stress","Practical tips and strategies for dealing with stress at work. Learn to set boundaries, manage your workload, and improve your work-life balance. stress, work, productivity, balance"
4,Meditation,"Guided Meditation for Sleep","A calming meditation to help you fall asleep faster and have a more restful night. Let go of the day's worries and drift into a deep sleep. sleep, anxiety, relaxation"
5,Article,"Understanding Cognitive Distortions","Learn about common negative thought patterns that contribute to anxiety and depression. This article helps you identify and challenge these distortions. anxiety, depression, cognitive behavioral therapy"
6,Breathing Exercise,"4-7-8 Breathing for Relaxation","A breathing exercise developed by Dr. Andrew Weil. It is a natural tranquilizer for the nervous system. Inhale for 4, hold for 7, and exhale for 8 seconds. Promotes deep relaxation and can help with sleep. sleep, relaxation, breathing, calm"
7,Article,"The Benefits of Journaling for Mental Health","Discover how writing down your thoughts and feelings can improve your mental well-being. A great tool for processing emotions and reducing stress. journaling, stress, self-reflection"
8,Meditation,"Meditation for Boosting Focus and Productivity","A guided session to help you sharpen your concentration and be more effective in your work. Clear mental clutter and enhance your cognitive performance. focus, productivity, work, mindfulness"

# src/recommender.py
import pandas as pd

# データセットの読み込み
try:
    df = pd.read_csv('mental_health_resources.csv')
    print("Dataset loaded successfully!")
    print(df.head())
except FileNotFoundError:
    print("Error: 'mental_health_resources.csv' not found. Please make sure the file is in the correct directory.")
    exit()

# コンテンツベースのレコメンダーでは、'description'に焦点を当てます
print("\
Resource Descriptions:")
print(df['description'])

# src/recommender.py (続き)
from sklearn.feature_extraction.text import TfidfVectorizer

# TfidfVectorizerの初期化
# stop_words='english'は、意味がほとんどない一般的な英語の単語
# ('the'、'a'、'in'など) を削除します
tfidf_vectorizer = TfidfVectorizer(stop_words='english')

# 説明テキストのfitとtransform
# これにより、説明から語彙と逆文書頻度を学習し、
# TF-IDF行列に変換します
tfidf_matrix = tfidf_vectorizer.fit_transform(df['description'])

# TF-IDF行列の形を見てみましょう
# 8行（8つのリソース）×一意の単語数だけの列があるはずです
print("\
Shape of TF-IDF Matrix:")
print(tfidf_matrix.shape)

# src/recommender.py (続き)
from sklearn.metrics.pairwise import cosine_similarity

def get_recommendations(user_input, top_n=3):
    """
    ユーザー入力に基づいて推奨を生成します
    """
    # 1. 同じTF-IDFベクトルizerを使用してユーザー入力を変換
    user_tfidf = tfidf_vectorizer.transform([user_input])

    # 2. ユーザーの入力とすべてのリソース間のコサイン類似度を計算
    # これにより、形状が(1, 8)の行列が得られ、各値は
    # ユーザー入力とリソース間の類似度スコアです
    cosine_similarities = cosine_similarity(user_tfidf, tfidf_matrix).flatten()

    # 3. 最も類似したリソースのインデックスを取得
    # argsortを使用して配列をソートするインデックスを取得し、
    # 反転してtop_n件を取得します
    related_docs_indices = cosine_similarities.argsort()[::-1][:top_n]

    # 4. 推奨リソースを返す
    recommendations = df.iloc[related_docs_indices]
    
    return recommendations

# --- テストしてみましょう！ ---
user_query = "I'm feeling anxious about work and can't sleep"
print(f"\
User Query: '{user_query}'")
recommended_resources = get_recommendations(user_query)

print("\
Recommended Resources:")
print(recommended_resources[['title', 'type', 'description']])

# src/mental_health_recommender.py

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

def load_data(filepath):
    """Loads the mental health resources dataset."""
    try:
        df = pd.read_csv(filepath)
        print("Dataset loaded successfully!")
        return df
    except FileNotFoundError:
        print(f"Error: '{filepath}' not found. Please check the file path.")
        return None

def create_recommender_components(df):
    """Creates the TF-IDF vectorizer and matrix."""
    tfidf_vectorizer = TfidfVectorizer(stop_words='english')
    tfidf_matrix = tfidf_vectorizer.fit_transform(df['description'])
    return tfidf_vectorizer, tfidf_matrix

def get_recommendations(user_input, df, tfidf_vectorizer, tfidf_matrix, top_n=3):
    """Generates and returns top N recommendations."""
    if df is None:
        return "Dataset not loaded. Cannot provide recommendations."

    user_tfidf = tfidf_vectorizer.transform([user_input])
    cosine_similarities = cosine_similarity(user_tfidf, tfidf_matrix).flatten()
    related_docs_indices = cosine_similarities.argsort()[::-1][:top_n]
    
    recommendations = df.iloc[related_docs_indices]
    return recommendations

if __name__ == '__main__':
    # Define the path to your dataset
    DATA_PATH = 'mental_health_resources.csv'
    
    # Load data and create recommender components
    resources_df = load_data(DATA_PATH)
    
    if resources_df is not None:
        vectorizer, matrix = create_recommender_components(resources_df)

        # Example usage of the recommender system
        user_query_1 = "I am feeling stressed and overwhelmed by my job"
        print(f"\
--- Recommendations for: '{user_query_1}' ---")
        recommendations_1 = get_recommendations(user_query_1, resources_df, vectorizer, matrix)
        print(recommendations_1[['title', 'type']])

        print("-" * 50)

        user_query_2 = "I want to be more mindful and improve my focus"
        print(f"\
--- Recommendations for: '{user_query_2}' ---")
        recommendations_2 = get_recommendations(user_query_2, resources_df, vectorizer, matrix)
        print(recommendations_2[['title', 'type']])