Pushing code

app.py

@@ -0,0 +1,66 @@
+import streamlit as st
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import linear_kernel
+from datasets import load_dataset
+
+# Load dataset from Hugging Face Datasets
+dataset = load_dataset("charizdiannefalco/imdb_top_1000")
+df = pd.DataFrame(dataset["train"])
+
+# Data cleaning.
+df['Overview'] = df['Overview'].fillna('')
+df['Gross'] = df['Gross'].fillna('0')
+df['Gross'] = df['Gross'].str.replace('$', '', regex=False).str.replace(',', '', regex=False).astype(float)
+
+# TF-IDF Vectorization
+tfidf = TfidfVectorizer(stop_words="english")
+tfidf_matrix = tfidf.fit_transform(df["Overview"])
+
+# Calculate Cosine Similarity
+cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
+
+# Function to get movie recommendations
+def get_recommendations(title, cosine_sim=cosine_sim, df = df):
+    idx = df[df["Series_Title"] == title].index[0]
+    sim_scores = list(enumerate(cosine_sim[idx]))
+    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
+    # Exclude the input movie itself
+    sim_scores = [score for score in sim_scores if score[0] != idx]
+    movie_indices = [i[0] for i in sim_scores]
+    movie_indices = movie_indices[0:3]
+    return df.iloc[movie_indices]
+
+# Streamlit App
+st.title("Movie Recommendation System")
+
+user_movies = st.multiselect("Enter movies you like:", df["Series_Title"].tolist())
+
+if st.button("Get Recommendations"):
+    if user_movies:
+        all_recommendations = pd.DataFrame()
+        for movie in user_movies:
+            all_recommendations = pd.concat([all_recommendations, get_recommendations(movie)])
+
+        #remove input movies from recommendations.
+        all_recommendations = all_recommendations[~all_recommendations['Series_Title'].isin(user_movies)]
+
+        all_recommendations = all_recommendations.drop_duplicates(subset=['Series_Title'])
+
+        if len(all_recommendations) > 3:
+            recommendations_df = all_recommendations.head(3)
+        else:
+            recommendations_df = all_recommendations
+
+        st.write("Recommended Movies:")
+        for index, row in recommendations_df.iterrows():
+            st.image(row["Poster_Link"], width=150)
+            st.write(f"**Title:** {row['Series_Title']}")
+            st.write(f"**Released Year:** {row['Released_Year']}")
+            st.write(f"**Runtime:** {row['Runtime']}")
+            st.write(f"**Genre:** {row['Genre']}")
+            st.write(f"**Overview:** {row['Overview']}")
+            st.write(f"**Director:** {row['Director']}")
+            st.write("---")
+    else:
+        st.warning("Please enter at least one movie.")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+scikit-learn
+pandas
+transformers
+datasets