init

Dockerfile

@@ -0,0 +1,9 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+CMD ["uvicorn", "api:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -1,9 +1,11 @@
 ---
-title: Prodrec
-emoji: 😻
-colorFrom: green
+title: Prodrectest
+emoji: 📉
+colorFrom: pink
 colorTo: blue
-sdk: docker
+sdk: streamlit
+sdk_version: 1.35.0
+app_file: app.py
 pinned: false
 license: mit
 ---

api.py

@@ -0,0 +1,25 @@
+from fastapi import FastAPI
+import joblib
+
+def show_recommendations(product):
+    Y = vectorizer.transform([product])
+    prediction = model.predict(Y)
+    return prediction,
+
+def get_cluster_terms(cluster_index):
+    cluster_terms = [terms[ind] for ind in order_centroids[cluster_index, :10]]
+    return cluster_terms
+
+model = joblib.load("./model.pkl")
+vectorizer = joblib.load("./vectorizer.pkl")
+
+order_centroids = model.cluster_centers_.argsort()[:, ::-1]
+terms = vectorizer.get_feature_names_out()
+
+app = FastAPI()
+
+@app.post("/inference")
+def get_recommendations(product: str):
+    cluster_index = int(show_recommendations(product)[0])
+    cluster_terms = get_cluster_terms(cluster_index)
+    return {"cluster": cluster_index, "top_terms": cluster_terms}

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.cluster import KMeans
+from fastapi import FastAPI
+import joblib
+
+def show_recommendations(product):
+    Y = vectorizer.transform([product])
+    prediction = model.predict(Y)
+    return prediction
+
+def print_cluster(i):
+    for ind in order_centroids[i, :10]:
+        print(' %s' % terms[ind]),
+
+def get_cluster_terms(cluster_index):
+    cluster_terms = [terms[ind] for ind in order_centroids[cluster_index, :10]]
+    return cluster_terms
+
+model = joblib.load("./model.pkl")
+vectorizer = joblib.load("./vectorizer.pkl")
+
+order_centroids = model.cluster_centers_.argsort()[:, ::-1]
+terms = vectorizer.get_feature_names_out()
+
+st.title("Product Recommendation System")
+
+# Input for product description
+product_input = st.text_input("Enter a product description:", "")
+
+# Button to trigger recommendation
+if st.button("Get Recommendations"):
+    if product_input:
+        # Get cluster for the input product
+        cluster_index = show_recommendations(product_input)[0]
+        
+        # Display the cluster number
+        st.write(f"The product belongs to cluster: {cluster_index}")
+        
+        # Display the top terms in the cluster
+        cluster_terms = get_cluster_terms(cluster_index)
+        st.write("Top terms in this cluster:")
+        st.write(", ".join(cluster_terms))
+    else:
+        st.write("Please enter a product description.")

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb889cc791652561f2c91b22cee7216ef634479ed86a5a7602de6f21f5f24ad6
+size 717173

train.py

@@ -0,0 +1,41 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.cluster import KMeans
+import pickle 
+
+product_descriptions = pd.read_csv("./train.csv")
+product_descriptions = product_descriptions.dropna()
+
+vectorizer = TfidfVectorizer(stop_words='english')
+X1 = vectorizer.fit_transform(product_descriptions["value"])
+
+true_k = 10
+model = KMeans(n_clusters=true_k, init='k-means++', max_iter=100, n_init=1)
+model.fit(X1)
+
+def show_recommendations(product):
+    Y = vectorizer.transform([product])
+    prediction = model.predict(Y)
+    return prediction
+
+def print_cluster(i):
+    for ind in order_centroids[i, :10]:
+        print(' %s' % terms[ind]),
+
+def get_cluster_terms(cluster_index):
+    cluster_terms = [terms[ind] for ind in order_centroids[cluster_index, :10]]
+    return cluster_terms
+
+order_centroids = model.cluster_centers_.argsort()[:, ::-1]
+terms = vectorizer.get_feature_names_out()
+
+print(print_cluster(show_recommendations("red dress")[0]))
+print(print_cluster(show_recommendations("water")[0]))
+print(print_cluster(show_recommendations("shoes")[0]))
+print(print_cluster(show_recommendations("cutting tool")[0]))
+
+pickle.dump(model, open("model.pkl", "wb"))
+pickle.dump(vectorizer, open("vectorizer.pkl", "wb"))
+
+
+

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ba96577981c278c57616ebfe977663c2e82e0be3e32282a517a50baaa99b35
+size 272049