Upload 8 files

app.py

@@ -0,0 +1,70 @@
+# app.py
+
+import joblib
+import pandas as pd
+import gradio as gr
+
+# Load the scaler and models
+scaler = joblib.load("models/scaler.joblib")
+models = {
+    "processing": joblib.load("models/svm_model_processing.joblib"),
+    "perception": joblib.load("models/svm_model_perception.joblib"),
+    "input": joblib.load("models/svm_model_input.joblib"),
+    "understanding": joblib.load("models/svm_model_understanding.joblib")
+}
+
+def predict(course_overview, reading_file, abstract_materiale, concrete_material, visual_materials,
+           self_assessment, exercises_submit, quiz_submitted, playing, paused, unstarted, buffering):
+    try:
+        input_data = {
+            "course_overview": [course_overview],
+            "reading_file": [reading_file],
+            "abstract_materiale": [abstract_materiale],
+            "concrete_material": [concrete_material],
+            "visual_materials": [visual_materials],
+            "self_assessment": [self_assessment],
+            "exercises_submit": [exercises_submit],
+            "quiz_submitted": [quiz_submitted],
+            "playing": [playing],
+            "paused": [paused],
+            "unstarted": [unstarted],
+            "buffering": [buffering]
+        }
+
+        input_df = pd.DataFrame(input_data)
+        input_scaled = scaler.transform(input_df)
+
+        predictions = {}
+        for target, model in models.items():
+            pred = model.predict(input_scaled)
+            predictions[target] = int(pred[0])
+
+        return predictions
+
+    except Exception as e:
+        return {"error": str(e)}
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.inputs.Number(label="Course Overview"),
+        gr.inputs.Number(label="Reading File"),
+        gr.inputs.Number(label="Abstract Materiale"),
+        gr.inputs.Number(label="Concrete Material"),
+        gr.inputs.Number(label="Visual Materials"),
+        gr.inputs.Number(label="Self Assessment"),
+        gr.inputs.Number(label="Exercises Submit"),
+        gr.inputs.Number(label="Quiz Submitted"),
+        gr.inputs.Number(label="Playing"),
+        gr.inputs.Number(label="Paused"),
+        gr.inputs.Number(label="Unstarted"),
+        gr.inputs.Number(label="Buffering")
+    ],
+    outputs="json",
+    title="SVM Multi-Target Prediction",
+    description="Enter the feature values to get predictions for processing, perception, input, and understanding."
+)
+
+if __name__ == "__main__":
+    iface.launch()

inference.py

@@ -0,0 +1,63 @@
+# inference.py
+
+import joblib
+import pandas as pd
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import List
+
+app = FastAPI()
+
+# Load the scaler and models at startup
+scaler = joblib.load("models/scaler.joblib")
+models = {
+    "processing": joblib.load("models/svm_model_processing.joblib"),
+    "perception": joblib.load("models/svm_model_perception.joblib"),
+    "input": joblib.load("models/svm_model_input.joblib"),
+    "understanding": joblib.load("models/svm_model_understanding.joblib")
+}
+
+# Define the input schema
+class InputData(BaseModel):
+    course_overview: float
+    reading_file: float
+    abstract_materiale: float
+    concrete_material: float
+    visual_materials: float
+    self_assessment: float
+    exercises_submit: float
+    quiz_submitted: float
+    playing: float
+    paused: float
+    unstarted: float
+    buffering: float
+
+class PredictionResponse(BaseModel):
+    processing: int
+    perception: int
+    input: int
+    understanding: int
+
+@app.post("/predict", response_model=PredictionResponse)
+def predict(data: InputData):
+    try:
+        # Convert input data to DataFrame
+        input_df = pd.DataFrame([data.dict()])
+        
+        # If there are categorical variables that were one-hot encoded during training,
+        # ensure that input data matches the training data's dummy variables.
+        # For simplicity, assuming all inputs are numerical and match the training features.
+
+        # Scale the input
+        input_scaled = scaler.transform(input_df)
+
+        # Make predictions for each target
+        predictions = {}
+        for target, model in models.items():
+            pred = model.predict(input_scaled)
+            predictions[target] = int(pred[0])
+
+        return predictions
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

models/scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d40f613f3b8b7bd9b51dc6b13631dd07ebdf6b373e41e6c5fd9d7cf20af814d
+size 1431

models/svm_model_input.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424a08119df19f4109d23e0d5f17084f0d3520c6a3c7eb2b137290dbf07e8d41
+size 34539

models/svm_model_perception.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e1f950e7427bde99c6de38bb977fb21217b36b1fa0eec4a4f68b2f58b0a99a
+size 30139

models/svm_model_processing.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6e8e1f74fb2d1f78144fd1cc820aa3af538459b07429d2e82abb9a3d2e5a2d
+size 68651

models/svm_model_understanding.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dac2d4345f1e12fb913694390fa16a77ab781ad209e8433db4dc98d3d132423
+size 53451

requirements.txt

@@ -0,0 +1,5 @@
+pandas
+joblib
+fastapi
+uvicorn
+scikit-learn==1.5.2