add req

app.py

@@ -1,15 +1,28 @@
 import os
 import wfdb
+import shutil
 import numpy as np
 import gradio as gr
 from models.inception import *
+from scipy.signal import resample
 
 
-def load_data():
-    cwd = os.getcwd()
-    sample_data = f"{cwd}/sample_data/ath_001"
-    ecg = wfdb.rdsamp(sample_data)
-    return np.asarray(ecg)
+def load_data(sample_data):
+    ecg, meta_data = wfdb.rdsamp(sample_data)
+    lead_I = ecg[:,0]
+    sample_frequency = meta_data["fs"]
+    return lead_I, sample_frequency
+
+def preprocess_ecg(ecg,fs):
+    if fs != 100:
+        ecg = resample(ecg, int(len(ecg)*(100/fs)))
+    else:
+        pass
+    if len(ecg) > 1000:
+        ecg = ecg[:1000]
+    else:
+        pass
+    return ecg
 
 def load_model(sample_frequency,recording_time, num_leads):
     cwd = os.getcwd()
@@ -19,14 +32,51 @@ def load_model(sample_frequency,recording_time, num_leads):
     return model
 
 
-def run(ecg):
+def run(header_file, data_file):
     SAMPLE_FREQUENCY = 100
     TIME = 10
     NUM_LEADS = 1
-    data = load_data()
+    demo_dir = f"{CWD}/sample_data"
+    _, hdr_basename = os.path.split(header_file.name)
+    _, data_basename = os.path.split(data_file.name)
+    shutil.copyfile(data_file.name, f"{demo_dir}/{data_basename}")
+    shutil.copyfile(header_file.name, f"{demo_dir}/{hdr_basename}")
+    data, fs = load_data(f"{demo_dir}/{hdr_basename.split('.')[0]}")
+    ecg = preprocess_ecg(data,fs)
     model = load_model(sample_frequency=SAMPLE_FREQUENCY,recording_time=TIME,num_leads=NUM_LEADS)
-    predicion = model.predict(data)
-    return predicion
+    predicion = model.predict(np.expand_dims(ecg,0)).ravel()[0]
+    return str(round(predicion,1))
+
+# Give credit to https://huggingface.co/spaces/Tej3/ECG_Classification/blob/main/app.py for interface
+
+CWD = os.getcwd()
+
+with gr.Blocks() as demo:
+    #with  gr.Row():
+    #    pred_type = gr.Radio(['Age', 'Gender'], label= "Select Model")
+    with gr.Row():
+        with gr.Column(scale=1):
+            header_file = gr.File(label = "header_file", file_types=[".hea"],)
+            data_file = gr.File(label = "data_file", file_types=[".dat"])
+        with gr.Column(scale=1):
+            output_age = gr.Textbox(label = "Predicted age")
+            #output_gender = gr.Textbox(label = "Predicted gender")
+    #with gr.Row():
+    #    ecg_graph = gr.Plot(label = "ECG Signal Visualisation")
+    with gr.Row():    
+        predict_btn = gr.Button("Predict")
+        predict_btn.click(fn= run, inputs = [#pred_type, 
+                                            header_file, data_file], outputs=[output_age])
+    with gr.Row():    
+        gr.Examples(examples=[[f"{CWD}/sample_data/ath_001.hea", f"{CWD}/sample_data/ath_001.dat"],\
+    #                          [f"{CWD}/demo_data/test/00008_lr.hea", f"{CWD}/demo_data/test/00008_lr.dat", "sinusrhythmus linkstyp qrs(t) abnormal    inferiorer infarkt     alter unbest."], \
+    #                          [f"{CWD}/demo_data/test/00045_lr.hea", f"{CWD}/demo_data/test/00045_lr.dat", "sinusrhythmus unvollstÄndiger rechtsschenkelblock sonst normales ekg"],\
+    #                          [f"{CWD}/demo_data/test/00257_lr.hea", f"{CWD}/demo_data/test/00257_lr.dat", "premature atrial contraction(s). sinus rhythm. left atrial enlargement. qs complexes in v2. st segments are slightly elevated in v2,3. st segments are depressed in i, avl. t waves are low or flat in i, v5,6 and inverted in avl. consistent with ischaemic h"],\
+                                ],
+                    inputs = [header_file, data_file])
+#
+if __name__ == "__main__":
+    demo.launch()
 
-iface = gr.Interface(fn=run, inputs="text", outputs="text")
-iface.launch()
+#iface = gr.Interface(fn=run, inputs="text", outputs="text")
+#iface.launch()

flagged/log.csv

@@ -0,0 +1,3 @@
+ecg,output,flag,username,timestamp
+1,,,,2024-01-13 13:13:14.648011
+1,,,,2024-01-13 13:13:16.151475

requirements.txt

@@ -0,0 +1,6 @@
+gradio==3.25.0
+numpy==1.24.2
+tqdm==4.64.1
+wfdb==4.1.0
+scipy==1.7.3
+tensorflow=2.8.0

sample_data/ath_001_2ztxkdc11326385fdd37d229683c95ce9ac5e9768817f96f.hea

@@ -0,0 +1,16 @@
+ath_001 12 500 5000
+ath_001.dat 16 50000/mV 16 0 10251 49595 0 I
+ath_001.dat 16 50000/mV 16 0 -1096 35223 0 II
+ath_001.dat 16 50000/mV 16 0 -10267 60826 0 III
+ath_001.dat 16 50000/mV 16 0 -3724 3505 0 AVR
+ath_001.dat 16 50000/mV 16 0 9391 26379 0 AVL
+ath_001.dat 16 50000/mV 16 0 -5395 57481 0 AVF
+ath_001.dat 16 50000/mV 16 0 13580 61759 0 V1
+ath_001.dat 16 50000/mV 16 0 11410 33501 0 V2
+ath_001.dat 16 50000/mV 16 0 14721 52508 0 V3
+ath_001.dat 16 50000/mV 16 0 16103 51083 0 V4
+ath_001.dat 16 50000/mV 16 0 6662 44197 0 V5
+ath_001.dat 16 50000/mV 16 0 -3806 11333 0 V6
+#SL12: Sinus bradycardia with marked sinus arrhythmia, Right axis deviation, Borderline ECG
+#C: Sinus arrhythmia,  Normal ECG
+

sample_data/ath_001_ewabg1uc1326385fdd37d229683c95ce9ac5e9768817f96f.hea

@@ -0,0 +1,16 @@
+ath_001 12 500 5000
+ath_001.dat 16 50000/mV 16 0 10251 49595 0 I
+ath_001.dat 16 50000/mV 16 0 -1096 35223 0 II
+ath_001.dat 16 50000/mV 16 0 -10267 60826 0 III
+ath_001.dat 16 50000/mV 16 0 -3724 3505 0 AVR
+ath_001.dat 16 50000/mV 16 0 9391 26379 0 AVL
+ath_001.dat 16 50000/mV 16 0 -5395 57481 0 AVF
+ath_001.dat 16 50000/mV 16 0 13580 61759 0 V1
+ath_001.dat 16 50000/mV 16 0 11410 33501 0 V2
+ath_001.dat 16 50000/mV 16 0 14721 52508 0 V3
+ath_001.dat 16 50000/mV 16 0 16103 51083 0 V4
+ath_001.dat 16 50000/mV 16 0 6662 44197 0 V5
+ath_001.dat 16 50000/mV 16 0 -3806 11333 0 V6
+#SL12: Sinus bradycardia with marked sinus arrhythmia, Right axis deviation, Borderline ECG
+#C: Sinus arrhythmia,  Normal ECG
+

sample_data/ath_001_rh_j77511326385fdd37d229683c95ce9ac5e9768817f96f.hea

@@ -0,0 +1,16 @@
+ath_001 12 500 5000
+ath_001.dat 16 50000/mV 16 0 10251 49595 0 I
+ath_001.dat 16 50000/mV 16 0 -1096 35223 0 II
+ath_001.dat 16 50000/mV 16 0 -10267 60826 0 III
+ath_001.dat 16 50000/mV 16 0 -3724 3505 0 AVR
+ath_001.dat 16 50000/mV 16 0 9391 26379 0 AVL
+ath_001.dat 16 50000/mV 16 0 -5395 57481 0 AVF
+ath_001.dat 16 50000/mV 16 0 13580 61759 0 V1
+ath_001.dat 16 50000/mV 16 0 11410 33501 0 V2
+ath_001.dat 16 50000/mV 16 0 14721 52508 0 V3
+ath_001.dat 16 50000/mV 16 0 16103 51083 0 V4
+ath_001.dat 16 50000/mV 16 0 6662 44197 0 V5
+ath_001.dat 16 50000/mV 16 0 -3806 11333 0 V6
+#SL12: Sinus bradycardia with marked sinus arrhythmia, Right axis deviation, Borderline ECG
+#C: Sinus arrhythmia,  Normal ECG
+

test.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import wfdb\n",
+    "import numpy as np\n",
+    "import gradio as gr\n",
+    "from models.inception import *\n",
+    "from scipy.signal import resample\n",
+    "\n",
+    "\n",
+    "def load_data():\n",
+    "    cwd = os.getcwd()\n",
+    "    sample_data = f\"{cwd}/sample_data/ath_001\"\n",
+    "    ecg, meta_data = wfdb.rdsamp(sample_data)\n",
+    "    lead_I = ecg[:,0]\n",
+    "    sample_frequency = meta_data[\"fs\"]\n",
+    "    return lead_I, sample_frequency\n",
+    "\n",
+    "def preprocess_ecg(ecg,fs):\n",
+    "    if fs != 500:\n",
+    "        ecg = resample(ecg, int(len(ecg)*(500/fs)))\n",
+    "    else:\n",
+    "        pass\n",
+    "    if len(ecg) > 5000:\n",
+    "        ecg = ecg[:5000]\n",
+    "    else:\n",
+    "        pass\n",
+    "    return ecg\n",
+    "\n",
+    "def load_model(sample_frequency,recording_time, num_leads):\n",
+    "    cwd = os.getcwd()\n",
+    "    weights = f\"{cwd}/models/weights/model_weights_leadI.h5\"\n",
+    "    model = build_model((sample_frequency * recording_time, num_leads), 1)\n",
+    "    model.load_weights(weights)\n",
+    "    return model\n",
+    "\n",
+    "\n",
+    "def run(ecg):\n",
+    "    SAMPLE_FREQUENCY = 100\n",
+    "    TIME = 10\n",
+    "    NUM_LEADS = 1\n",
+    "    data, fs = load_data()\n",
+    "    model = load_model(sample_frequency=SAMPLE_FREQUENCY,recording_time=TIME,num_leads=NUM_LEADS)\n",
+    "    predicion = model.predict(data)\n",
+    "    return str(predicion)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data, fs = load_data()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5000,)"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out = preprocess_ecg(data,250)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5000,)"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "out[:5000].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.5"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "500/1000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "upsamp = preprocess_ecg(data,1000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.])"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "upsamp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "new_tf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}