Personalized Music And Movie Recommendation System

Overview

A real-time emotion detection system that recommends movies and music based on a person's detected emotion.

Tools and Libraries Used

Programming Language:

Python

Libraries:

OpenCV: For capturing and processing images.
Deep Learning Framework: Tensorflow/Keras.
Machine Learning Libraries: Pandas, Numpy.
Importing Model: Joblib.

Dataset Collection

Emotion Dataset/Images: Use publicly available datasets like in kaggle.
Classes: Define emotions (e.g., Happy, Sad, Angry, Neutral, Disguist, Fear, Surprise etc.).
Movies and Music Dataset: Use publicly available datasets like in kaggle.

Music Recommendation

Create a function which give the music based on the mood of the person.

# def music_recom(Emotion):
    filter=df[df['Emotion']==Emotion]
    if not filter.empty:
        top_music=filter.iloc[:5]['Name']
        print("\n".join(top_music))
    else:
        print(f"No music found for the emotion:{Emotion}")

Movie Recommendation

Create a function which give the movie based on the mood of the person.

# emotion_to_genre = {
    'Sad': 'Drama',
    'Disguist': 'Crime',
    'Anger': 'Action',
    'Happy': 'Comedy',
    'Neutral': 'Family',
    'Surprise': 'Fantasy',
    'Fear': 'Horror',
}
def recommend(Emotion):
    genre=emotion_to_genre.get(Emotion)

    if genre:
        filter=df[df['Genre'].str.contains(genre,case=False,na=False)]
        if not filter.empty:
            top_movies=filter.iloc[:5]['Movie_Name']
            print("\n".join(top_movies))
        else:
            print(f"No movie found for the genre: {genre}")
    else:
        print(f"No genre found for the emotion:{Emotion}")

Emotion Detection System

Detect the emotion of the person and give the music and movie recommendation to person. For detecting the emotion i used the cnn model and keras libraries.

# model=Sequential()
model.add(Conv2D(128,kernel_size=(3,3),activation='relu',input_shape=(64,64,1)))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.4))

model.add(Conv2D(256,kernel_size=(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.4))

model.add(Conv2D(512,kernel_size=(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.4))

model.add(Conv2D(512,kernel_size=(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.4))

model.add(Flatten())
model.add(Dense(512,activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(256,activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(7,activation='softmax'))