Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tmdb_5000_credits.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,95 @@
+import numpy as np
+import pandas as pd
+import ast
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from nltk.stem.porter import PorterStemmer
+import gradio as gr
+import nltk
+nltk.download('punkt')
+
+# Load data
+movies = pd.read_csv('tmdb_5000_movies.csv')
+credits = pd.read_csv('tmdb_5000_credits.csv')
+movies = movies.merge(credits, on='title')
+movies = movies[['movie_id', 'title', 'overview', 'genres', 'keywords', 'cast', 'crew']]
+movies.dropna(inplace=True)
+
+
+# Process genres, keywords
+def convert(obj):
+    return [i['name'].replace(" ", "") for i in ast.literal_eval(obj)]
+
+
+movies['genres'] = movies['genres'].apply(convert)
+movies['keywords'] = movies['keywords'].apply(convert)
+
+
+# Top 3 cast
+def convert3(obj):
+    return [i['name'].replace(" ", "") for i in ast.literal_eval(obj)[:3]]
+
+
+movies['cast'] = movies['cast'].apply(convert3)
+
+
+# Director
+def fetch_director(obj):
+    for i in ast.literal_eval(obj):
+        if i['job'] == 'Director':
+            return [i['name'].replace(" ", "")]
+    return []
+
+
+movies['crew'] = movies['crew'].apply(fetch_director)
+
+# Overview processing
+movies['overview'] = movies['overview'].apply(lambda x: x.split())
+
+# Create tags
+movies['tags'] = movies['overview'] + movies['genres'] + movies['keywords'] + movies['cast'] + movies['crew']
+new_df = movies[['movie_id', 'title', 'tags']]
+new_df['tags'] = new_df['tags'].apply(lambda x: " ".join(x).lower())
+
+# Stemming
+ps = PorterStemmer()
+
+
+def stem(text):
+    return " ".join([ps.stem(word) for word in text.split()])
+
+
+new_df['tags'] = new_df['tags'].apply(stem)
+
+# Vectorization
+cv = CountVectorizer(max_features=5000, stop_words='english')
+vectors = cv.fit_transform(new_df['tags']).toarray()
+
+# Similarity
+similarity = cosine_similarity(vectors)
+
+
+# Recommendation function
+def recommend(movie):
+    movie = movie.lower()
+    if movie not in new_df['title'].str.lower().values:
+        return ["Movie not found in database :( "]
+
+    index = new_df[new_df['title'].str.lower() == movie].index[0]
+    distances = similarity[index]
+    movie_list = sorted(enumerate(distances), reverse=True, key=lambda x: x[1])[1:6]
+    return [new_df.iloc[i[0]].title for i in movie_list]
+
+
+# Gradio interface
+def recommend_interface(movie_name):
+    return recommend(movie_name)
+
+
+demo = gr.Interface(fn=recommend_interface,
+                    inputs=gr.Textbox(lines=1, placeholder="Enter a movie name..."),
+                    outputs=gr.List(label="Top 5 Recommendations"),
+                    title="Movie Recommender")
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+pandas
+numpy
+nltk
+scikit-learn

tmdb_5000_credits.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0050599ff88d40366c4841204b1489862bca346bfa46c20b05a65d14508435
+size 40044293