Add model.joblib, update Dockerfile and

Dockerfile

@@ -1,5 +1,5 @@
 # Use the official Python 3.9 image
-FROM python:3.9
+FROM python:3.9-slim
 
 # Set the working directory to /code
 WORKDIR /code

app.py

@@ -1,11 +1,70 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, UploadFile, File
+import numpy as np
+from sklearn.neural_network import MLPRegressor
+from sklearn.model_selection import KFold
+from sklearn.metrics import mean_squared_error
+import csv
+import io
+
+from joblib import load, dump
+
+# Load the model
+model = load("model.joblib")
 
 # Create a new FastAPI app instance
 app = FastAPI(docs_url="/", redoc_url="/new_redoc")
 
 
 # Create a POST endpoint
-@app.get("/generate")
-def generate(text: str):
-    """Traduce del castellano al inglés"""
-    return {"output": text}
+@app.get("/generate/{squareFeet}/{bedrooms}/{bathrooms}/{yearBuilt}")
+def generate(
+    squareFeet: float,
+    bedrooms: float,
+    bathrooms: float,
+    yearBuilt: float,
+):
+    global model
+    prediction = model.predict([[squareFeet, bedrooms, bathrooms, yearBuilt]])
+    return {"output": prediction[0]}
+
+
+@app.post("/train")
+async def train(file: UploadFile = File(...)):
+    global model
+
+    contents = await file.read()
+    data = list(csv.reader(io.StringIO(contents.decode("utf-8"))))
+
+    data_np = np.array(data[1:], dtype=object)
+
+    # Delete the fourth column
+    data_np = np.delete(data_np, 3, axis=1)
+    data_np = np.array(data_np, dtype=float)
+
+    # All columns except the last
+    X = data_np[:, :-1]
+
+    # Only the last column
+    y = data_np[:, -1]
+    y = np.ravel(y)
+
+    # Fit the model
+    kf = KFold(n_splits=4)
+    accuracies = []
+
+    for train_index, test_index in kf.split(X):
+        X_train, X_test = X[train_index], X[test_index]
+        y_train, y_test = y[train_index], y[test_index]
+
+        model.fit(X_train, y_train)
+
+        predictions = model.predict(X_test)
+        rmse = np.sqrt(mean_squared_error(y_test, predictions))
+        accuracies.append(rmse)
+
+    average_rmse = sum(accuracies) / len(accuracies)
+    print(f"Average RMSE: {average_rmse}")
+
+    dump(model, "model.joblib")
+
+    return {"filename": file.filename, "average_rmse": average_rmse}

requirements.txt

@@ -1,6 +1,30 @@
-fastapi==0.74.*
-requests==2.27.*
-uvicorn[standard]==0.17.*
-sentencepiece==0.1.*
-torch==1.11.*
-#transformers==4.*
+# requirements.txt
+
+anyio==3.7.1
+asgiref==3.7.2
+certifi==2023.11.17
+charset-normalizer==2.0.12
+click==8.1.7
+fastapi==0.74.1
+h11==0.14.0
+httptools==0.6.1
+idna==3.6
+joblib==1.3.2
+numpy==1.26.2
+pydantic==1.10.13
+python-dotenv==1.0.0
+python-multipart==0.0.6
+PyYAML==6.0.1
+requests==2.27.1
+scikit-learn==1.3.2
+scipy==1.11.4
+sentencepiece==0.1.99
+sniffio==1.3.0
+starlette==0.17.1
+threadpoolctl==3.2.0
+typing_extensions==4.8.0
+urllib3==1.26.18
+uvicorn==0.17.6
+uvloop==0.19.0
+watchgod==0.8.2
+websockets==12.0