Upload proyecto_buscar_pelicula.py

proyecto_buscar_pelicula.py

@@ -0,0 +1,145 @@
+# -*- coding: utf-8 -*-
+"""Proyecto-buscar-pelicula.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1gfkDWGdNI04qm8HP1wp0dTGy40UmhOQG
+"""
+
+# Commented out IPython magic to ensure Python compatibility.
+# %%capture
+# !pip install -U sentence-transformers
+# !pip install gradio chromadb
+
+import pandas as pd
+from sentence_transformers import SentenceTransformer, util
+from ast import literal_eval
+import chromadb
+from chromadb.utils import embedding_functions
+
+import gdown
+
+url = 'https://drive.google.com/uc?id='
+file_id = '1MgM3iObIAdqA-SvI-pXeUeXEiEAuMzXw'
+output = '25k IMDb movie Dataset.csv'
+
+gdown.download(url+file_id, output, quiet=False)
+
+df = pd.read_csv(output)
+
+def concatenar_lista(lista):
+    lista = literal_eval(lista)
+    return ' '.join(lista)
+
+def string_to_list(lista):
+    lista = literal_eval(lista)
+    return lista
+
+df = df.fillna(' ')
+
+df['Keywords'] = df['Plot Kyeword'].apply(concatenar_lista)
+
+df['Stars'] = df['Top 5 Casts'].apply(concatenar_lista)
+
+df['Generes'] = df['Generes'].apply(string_to_list)
+
+df['Rating'] = pd.to_numeric(df['Rating'], errors="coerce").fillna(0).astype("float")
+
+unique_generes = df['Generes'].explode().unique()
+
+df.drop(['Plot Kyeword','Top 5 Casts'],axis=1, inplace=True)
+
+df['text'] = df.apply(lambda x: str(x['Overview']) + ' ' + x['Keywords'] + ' ' + x['Stars'], axis=1)
+
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+embeddings = model.encode(df['text'],batch_size=64,show_progress_bar=True)
+
+df['embeddings'] = embeddings.tolist()
+
+df['ids'] = df.index
+
+df['ids'] = df['ids'].astype('str')
+
+client_persistent = chromadb.PersistentClient(path='data_embeddings')
+
+db = client_persistent.create_collection(name='movies_db')
+
+df['Generes'] = df['Generes'].apply(lambda x: ', '.join(x))
+
+from torch import embedding
+db.add(
+    ids = df['ids'].tolist(),
+    embeddings = df['embeddings'].tolist(),
+    metadatas = df.drop(['ids', 'embeddings', 'text'], axis=1).to_dict('records')
+)
+
+from chromadb.api.types import Metadatas
+
+def search(query, genre, rating, num):
+    num = int(num)
+    if rating:
+        filter_rating = rating
+    else:
+        filter_rating = 0
+
+    if genre:
+        conditions = {
+            "$and": [
+            {"Generes": genre},
+            {"Rating": {"$gte": filter_rating}}
+            ]
+        }
+    else:
+        conditions = {
+            "Rating": {"$gte": filter_rating}
+        }
+
+    responses = db.query(
+        query_texts=[query],
+        n_results=num,
+        where=conditions,
+        include=['metadatas']
+
+    )
+
+    response_data = []
+
+    for response in responses['metadatas']:
+      for metadata in response:
+        if not isinstance(genre, list):
+            genre = [genre]
+        response_data.append({
+            'Title': metadata['movie title'],
+            'Overview': metadata['Overview'],
+            'Director': metadata['Director'],
+            'Stars': metadata['Stars'],
+            'Genre':  metadata['Generes'],
+            'year': metadata['year'],
+            'Rating': metadata['Rating']
+        })
+
+
+    df = pd.DataFrame(response_data)
+
+    return df
+
+import gradio as gr
+
+genres = unique_generes.tolist()
+iface = gr.Interface(
+    fn=search,
+    inputs=[
+        gr.Textbox(lines=5, placeholder="Escribe aquí tu consulta...", label="Consulta"),
+        gr.Dropdown(choices=genres, label="Género de la película"),
+        gr.Slider(minimum=1, maximum=10, value=5, label="Puntuación mínima"),
+        gr.Number(minimum=1, maximum=10, value=3, label="Número de resultados")
+
+    ],
+    outputs=gr.Dataframe(type="pandas",label="Resultados"),
+    title="Buscador de películas",
+    description="Introduce tu consulta, selecciona un género y define una puntuación mínima para buscar películas."
+)
+
+iface.launch(share=False)