first commit

Dockerfile

@@ -0,0 +1,14 @@
+# Use the official Python 3.10.9 image
+FROM python:3.10.9
+
+# Copy the current directory contents into the container at .
+COPY . .
+
+# Set the working directory to /
+WORKDIR /
+
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /requirements.txt
+
+# Start the FastAPI app on port 7860, the default port expected by Spaces
+CMD ["uvicorn", "recommender:app", "--host", "0.0.0.0", "--port", "7860"]

preprocessed_data.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b741a71fb861485395ecea86b14ff7b5e190bed8da5b06fc9feb841bcf3ef355
+size 67792

recommender.py

@@ -0,0 +1,35 @@
+from fastapi import FastAPI, Body
+import pickle
+
+with open('preprocessed_data.pkl', 'rb') as f:
+    tfidf_matrix, cosine_sim_tfidf, df, indices = pickle.load(f)
+
+app = FastAPI()
+
+@app.post("/recommendations")
+def recommend(course_data: dict = Body(...)):
+  idx = indices.get(course_data["title"])
+
+  # Handle cases where the course title is not found
+  if idx is None:
+      return {"message": "Course not found."}
+
+  # Get the pairwise similarity scores of all courses with that course
+  sim_scores = list(enumerate(cosine_sim_tfidf[idx]))
+
+  # Sort the courses based on the similarity scores
+  sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
+
+  # Get the scores of the 10 most similar courses
+  sim_scores = sim_scores[1:11]
+
+  # Get the course indices
+  course_indices = [i[0] for i in sim_scores]
+
+  recommendations = df.iloc[course_indices][['CourseID', 'Title']].to_dict(orient='records')
+
+  return recommendations
+
+if __name__ == "__main__":
+  import uvicorn
+  uvicorn.run("recommender:app", host="0.0.0.0", port=3000)

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+scipy
+pandas