initial commit

README.md

@@ -1,13 +0,0 @@
----
-title: DataMining
-emoji: 🦀
-colorFrom: green
-colorTo: indigo
-sdk: gradio
-sdk_version: 4.7.1
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+import torch, numpy as np, pandas as pd
+import skimage 
+import pickle
+
+defaultColumns = ['movieId', 'rating']
+
+movies_df = pd.read_csv("./csv/movies.csv")
+ratings_df = pd.read_csv("./csv/ratings.csv")
+
+options = movies_df['title'].values
+
+with open("model.pkl", "rb") as f:
+    model = pickle.load(f)
+
+def recomendacao(filme, nota):
+
+    f_filme = movies_df.loc[movies_df['title'] == filme]['movieId'][0]
+    f_nota = float(nota) 
+
+    default = [
+        f_filme,
+        f_nota
+    ]
+
+    df=pd.DataFrame([default], columns = defaultColumns)
+
+    predictions = model.predict(df)
+
+    user_rating = ratings_df.loc[ratings_df['userId'] == predictions[0]]
+    top_ratings = user_rating.sort_values(by='rating', ascending=False)
+    
+    top_movies = top_ratings.head(5)['movieId'].tolist()
+
+    recomendacoes = []
+    for movie_id in top_movies:
+        movie = movies_df.loc[movies_df['movieId'] == movie_id]
+        title = movie['title'].values[0]
+        recomendacoes.append(title)
+    recomendacoes
+
+    result = recomendacoes
+
+    return result
+
+iface = gr.Interface(
+    fn=recomendacao,
+    title="Win Predict",
+    allow_flagging="never",
+    inputs=[
+        gr.Dropdown(options, label="Filme", info="Escolha o nome de um filme"),
+        gr.Slider(0, 5, value=0, label="Rating", info="Dê uma nota entre 0 e 5"),
+    ],
+    outputs="text")
+iface.launch()

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca77c01c99177b42b4ca4e4e9bd55abc1266d14fa126f284cec36569897aea20
+size 92787829

requirements.txt

@@ -0,0 +1,3 @@
+fastai
+scikit-image
+pandas