Sync API from main repo

fast.py

@@ -2,7 +2,7 @@ from fastapi import FastAPI, File, UploadFile, HTTPException
 from huggingface_hub import hf_hub_download
 
 from utils import load_model_by_type, encoder_from_model
-from preproc import label_decoding
+from preproc import label_decoding, apple_csv_to_data, apple_extract_beats
 import pandas as pd
 from io import StringIO
 from pathlib import Path
@@ -74,6 +74,22 @@ async def predict(model_name: str, filepath_csv: UploadFile = File(...)):
     
     return {"prediction": y_pred}
 
+@app.post("/predict_multibeats")
+async def predict_multibeats(model_name: str, filepath_csv: UploadFile = File(...)):
+    model = app.state.model = model_loader(model_name)
+
+    # Read the uploaded CSV file
+    file_content = await filepath_csv.read()
+    # X = pd.read_csv(StringIO(file_content.decode('utf-8')))
+    X, sample_rate = apple_csv_to_data(file_content)
+    beats = apple_extract_beats(X, sample_rate)
+    y_pred = model.predict_with_pipeline(beats)
+    
+    # Decode prediction using absolute path
+    
+    y_pred = label_decoding(values=y_pred, path=encoder_cache[model_name])
+    
+    return {"prediction": y_pred}
 
 # @app.post("/predict_multibeats")
 # async def predict_multibeats(model_name: str, filepath_csv: UploadFile = File(...)):

preproc.py

@@ -1,9 +1,11 @@
 from tslearn.utils import to_time_series_dataset
 from tslearn.preprocessing import TimeSeriesScalerMeanVariance
 import pickle
-from wfdb import rdrecord, rdann, processing
+from wfdb import processing
 from sklearn import preprocessing
 from scipy.signal import resample
+from io import StringIO
+
 
 import numpy as np
 import pandas as pd
@@ -20,19 +22,19 @@ def preproc(X):
     X = scaler.fit_transform(X)
     return X.reshape(in_shape)
 
-def apple_csv_to_data(filepath_csv):
+def apple_csv_to_data(file_content):
     # extract sampling rate 
-    with open(filepath_csv, 'r') as file:
-        for il,line in enumerate(file):
-            if line.startswith("Sample Rate"):
-                # Extract the sample rate
-                sample_rate = int(line.split(",")[1].split()[0])  # Split and get the numerical part
-                print(f"Sample Rate: {sample_rate}")
-                break
-            if il > 30:
-                print("Could not find sample rate in first 30 lines")
-                return None, None  
-    X = pd.read_csv(filepath_csv, skiprows=14, header=None)
+
+    for il,line in enumerate(file_content.decode('utf-8').splitlines()):
+        if line.startswith("Sample Rate"):
+            # Extract the sample rate
+            sample_rate = int(line.split(",")[1].split()[0])  # Split and get the numerical part
+            print(f"Sample Rate: {sample_rate}")
+            break
+        if il > 30:
+            print("Could not find sample rate in first 30 lines")
+            return None, None  
+    X = pd.read_csv(StringIO(file_content.decode('utf-8')), skiprows=14, header=None)
     return X, sample_rate
 
 def apple_trim_join(X, sample_rate=512, ns=2):