Build a quote recommendation system

Here’s a basic Quote Recommendation System built using Python. This system recommends quotes to users based on their preferred categories using content-based filtering. For simplicity, it works offline with a static dataset of quotes.

🛠 Requirements

• Python 3.7+

• pandas

• sklearn

Install dependencies:

bash
CopyEdit
pip install pandas scikit-learn

📁 Step-by-Step Code

python
CopyEdit
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# Sample quotes dataset
data = [
    {"quote": "The only limit to our realization of tomorrow is our doubts of today.", "author": "Franklin D. Roosevelt", "tags": "inspiration, future"},
    {"quote": "In the middle of every difficulty lies opportunity.", "author": "Albert Einstein", "tags": "inspiration, motivation"},
    {"quote": "Life is what happens when you're busy making other plans.", "author": "John Lennon", "tags": "life, reality"},
    {"quote": "Success is not final, failure is not fatal: It is the courage to continue that counts.", "author": "Winston Churchill", "tags": "success, courage"},
    {"quote": "Happiness depends upon ourselves.", "author": "Aristotle", "tags": "happiness, self"},
    {"quote": "The purpose of our lives is to be happy.", "author": "Dalai Lama", "tags": "life, happiness"},
]

# Load into DataFrame
df = pd.DataFrame(data)

# Vectorize the tags using TF-IDF
tfidf = TfidfVectorizer(stop_words='english')
tfidf_matrix = tfidf.fit_transform(df['tags'])

# Compute cosine similarity matrix
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# Mapping from quote index to tags
indices = pd.Series(df.index, index=df['tags'])

# Recommendation function
def recommend_quotes(input_tag, top_n=3):
    input_vec = tfidf.transform([input_tag])
    sim_scores = linear_kernel(input_vec, tfidf_matrix).flatten()
    sim_indices = sim_scores.argsort()[::-1][:top_n]
    
    recommendations = df.iloc[sim_indices][['quote', 'author']]
    return recommendations

# Example usage
user_interest = "happiness"
results = recommend_quotes(user_interest)

for i, row in results.iterrows():
    print(f'"{row.quote}" — {row.author}')

🔄 Sample Output

If the user inputs "happiness":

arduino
CopyEdit
"The purpose of our lives is to be happy." — Dalai Lama  
"Happiness depends upon ourselves." — Aristotle  
"Life is what happens when you're busy making other plans." — John Lennon  

🔧 Optional Enhancements

• Add a user feedback loop (like/dislike) and re-rank quotes.

• Use NLP embeddings (like BERT) for deeper semantic understanding.

• Store user preferences in a database.

• Build a REST API using Flask or FastAPI for production deployment.

• Add filters by author or time period.

Let me know if you’d like a web-based UI or database integration version.