From 3dfc1beec810411058fae64f9fa07c3262831230 Mon Sep 17 00:00:00 2001 From: s434766 Date: Fri, 7 May 2021 21:30:35 +0200 Subject: [PATCH] jobs --- Dockerfile | 4 +- lab5.ipynb | 97 +++--------------- {pytorch => pytorch-training-eval}/Dockerfile | 3 +- pytorch-training-eval/Jenkinsfile-eval | 32 ++++++ .../Jenkinsfile-train | 16 +-- stroke-pytorch-eval.py | 50 +++++++++ stroke-pytorch.py | 14 +-- stroke.pkl | Bin 1855 -> 0 bytes stroke.pth | Bin 0 -> 1151 bytes 9 files changed, 118 insertions(+), 98 deletions(-) rename {pytorch => pytorch-training-eval}/Dockerfile (66%) create mode 100644 pytorch-training-eval/Jenkinsfile-eval rename pytorch/Jenkinsfile => pytorch-training-eval/Jenkinsfile-train (51%) create mode 100644 stroke-pytorch-eval.py delete mode 100644 stroke.pkl create mode 100644 stroke.pth diff --git a/Dockerfile b/Dockerfile index ee2303f..a623080 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,10 +1,10 @@ FROM ubuntu:latest -RUN apt-get update && apt-get install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn && rm -rf /var/lib/apt/lists/* +RUN apt-get update && apt-get install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn && pip3 install matplotlib && rm -rf /var/lib/apt/lists/* RUN pip3 install torch torchvision torchaudio WORKDIR /app COPY ./create.py ./ COPY ./stats.py ./ COPY ./stroke-pytorch.py ./ - +COPY ./stroke-pytorch-eval.py ./ diff --git a/lab5.ipynb b/lab5.ipynb index 8bf80c1..57944f4 100644 --- a/lab5.ipynb +++ b/lab5.ipynb @@ -10,7 +10,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.5-final" + "version": "3.8.5" }, "orig_nbformat": 2, "kernelspec": { @@ -23,7 +23,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 74, "metadata": {}, "outputs": [], "source": [ @@ -50,7 +50,7 @@ " out = self.linear(x)\n", " return self.sigmoid(out)\n", "\n", - "\n", + "np.set_printoptions(suppress=False)\n", "data_train = pd.read_csv(\"data_train.csv\")\n", "data_test = pd.read_csv(\"data_test.csv\")\n", "data_val = pd.read_csv(\"data_val.csv\")\n", @@ -59,7 +59,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 75, "metadata": {}, "outputs": [], "source": [ @@ -80,19 +80,19 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 76, "metadata": {}, "outputs": [], "source": [ "\n", - "batch_size = 95\n", + "batch_size = 150\n", "n_iters = 1000\n", - "num_epochs = int(n_iters / (len(x_train) / batch_size))" + "num_epochs = 10" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 77, "metadata": {}, "outputs": [], "source": [ @@ -104,7 +104,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 78, "metadata": {}, "outputs": [], "source": [ @@ -116,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 79, "metadata": {}, "outputs": [ { @@ -134,79 +134,14 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 80, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "Epoch # 0\n", - "4.4554009437561035\n", - "Epoch # 1\n", - "2.887434244155884\n", - "Epoch # 2\n", - "1.4808591604232788\n", - "Epoch # 3\n", - "0.6207292079925537\n", - "Epoch # 4\n", - "0.4031478762626648\n", - "Epoch # 5\n", - "0.34721270203590393\n", - "Epoch # 6\n", - "0.32333147525787354\n", - "Epoch # 7\n", - "0.3105970621109009\n", - "Epoch # 8\n", - "0.30295372009277344\n", - "Epoch # 9\n", - "0.2980167269706726\n", - "Epoch # 10\n", - "0.29466450214385986\n", - "Epoch # 11\n", - "0.29230451583862305\n", - "Epoch # 12\n", - "0.29059702157974243\n", - "Epoch # 13\n", - "0.2893349230289459\n", - "Epoch # 14\n", - "0.2883857190608978\n", - "Epoch # 15\n", - "0.2876618504524231\n", - "Epoch # 16\n", - "0.2871031165122986\n", - "Epoch # 17\n", - "0.28666743636131287\n", - "Epoch # 18\n", - "0.28632479906082153\n", - "Epoch # 19\n", - "0.2860531508922577\n", - "Epoch # 20\n", - "0.28583624958992004\n", - "Epoch # 21\n", - "0.2856619954109192\n", - "Epoch # 22\n", - "0.285521000623703\n", - "Epoch # 23\n", - "0.2854064106941223\n", - "Epoch # 24\n", - "0.2853126525878906\n", - "Epoch # 25\n", - "0.2852354049682617\n", - "Epoch # 26\n", - "0.2851715385913849\n", - "Epoch # 27\n", - "0.28511837124824524\n", - "Epoch # 28\n", - "0.2850736975669861\n", - "Epoch # 29\n", - "0.2850360572338104\n", - "Epoch # 30\n", - "0.28500401973724365\n", - "Epoch # 31\n", - "0.2849765419960022\n", - "X:\\Anaconda2020\\lib\\site-packages\\torch\\autograd\\__init__.py:145: UserWarning: CUDA initialization: The NVIDIA driver on your system is too old (found version 10010). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver. (Triggered internally at ..\\c10\\cuda\\CUDAFunctions.cpp:109.)\n", - " Variable._execution_engine.run_backward(\n" + "Epoch # 0\n0.34391772747039795\nEpoch # 1\n0.3400452435016632\nEpoch # 2\n0.33628249168395996\nEpoch # 3\n0.3326331079006195\nEpoch # 4\n0.3291005790233612\nEpoch # 5\n0.32568827271461487\nEpoch # 6\n0.32239940762519836\nEpoch # 7\n0.3192369043827057\nEpoch # 8\n0.3162035048007965\nEpoch # 9\n0.31330153346061707\n" ] } ], @@ -227,7 +162,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 81, "metadata": { "tags": [] }, @@ -236,7 +171,7 @@ "output_type": "stream", "name": "stdout", "text": [ - "predicted Y value: tensor([[0.0468],\n [0.0325],\n [0.2577],\n [0.2059],\n [0.1090],\n [0.0229],\n [0.2290],\n [0.0689],\n [0.2476],\n [0.0453],\n [0.0150],\n [0.4080],\n [0.0424],\n [0.0981],\n [0.0221],\n [0.1546],\n [0.1400],\n [0.1768],\n [0.1684],\n [0.0229],\n [0.1836],\n [0.1200],\n [0.0137],\n [0.2316],\n [0.0185],\n [0.0179],\n [0.0108],\n [0.0175],\n [0.0471],\n [0.4576],\n [0.0210],\n [0.0103],\n [0.0616],\n [0.1850],\n [0.4114],\n [0.4264],\n [0.0405],\n [0.0788],\n [0.2405],\n [0.0340],\n [0.4345],\n [0.1758],\n [0.0385],\n [0.0749],\n [0.4349],\n [0.0357],\n [0.0295],\n [0.3939],\n [0.1147],\n [0.3812],\n [0.0659],\n [0.0675],\n [0.0263],\n [0.1398],\n [0.0959],\n [0.0406],\n [0.0531],\n [0.0500],\n [0.4259],\n [0.1086],\n [0.0611],\n [0.0855],\n [0.0473],\n [0.2826],\n [0.1734],\n [0.0560],\n [0.0466],\n [0.0290],\n [0.1903],\n [0.4515],\n [0.0118],\n [0.2158],\n [0.1293],\n [0.2488],\n [0.0424],\n [0.1809],\n [0.0122],\n [0.0796],\n [0.0901],\n [0.0879],\n [0.0457],\n [0.0091],\n [0.0196],\n [0.3310],\n [0.0978],\n [0.0843],\n [0.0684],\n [0.0340],\n [0.0583],\n [0.0670],\n [0.0133],\n [0.1165],\n [0.0145],\n [0.1581],\n [0.1677],\n [0.0353],\n [0.0745],\n [0.0108],\n [0.0492],\n [0.0611],\n [0.2977],\n [0.2820],\n [0.0219],\n [0.0580],\n [0.0122],\n [0.0726],\n [0.3315],\n [0.0201],\n [0.2460],\n [0.0110],\n [0.0322],\n [0.0180],\n [0.0135],\n [0.3176],\n [0.1390],\n [0.0678],\n [0.1596],\n [0.0128],\n [0.0900],\n [0.0117],\n [0.0224],\n [0.0357],\n [0.0103],\n [0.1728],\n [0.0135],\n [0.0992],\n [0.4371],\n [0.4525],\n [0.0278],\n [0.0617],\n [0.2499],\n [0.0129],\n [0.0424],\n [0.0292],\n [0.3903],\n [0.0108],\n [0.0404],\n [0.0344],\n [0.4109],\n [0.3936],\n [0.0603],\n [0.4396],\n [0.1155],\n [0.3594],\n [0.0305],\n [0.0307],\n [0.0226],\n [0.1284],\n [0.0474],\n [0.0959],\n [0.0135],\n [0.0289],\n [0.3705],\n [0.1538],\n [0.4535],\n [0.0355],\n [0.0169],\n [0.1648],\n [0.4217],\n [0.0951],\n [0.0767],\n [0.0475],\n [0.0452],\n [0.1625],\n [0.0896],\n [0.0114],\n [0.0423],\n [0.3971],\n [0.0173],\n [0.0250],\n [0.3579],\n [0.0131],\n [0.0201],\n [0.0149],\n [0.2615],\n [0.1773],\n [0.1204],\n [0.3556],\n [0.2390],\n [0.0098],\n [0.0190],\n [0.3040],\n [0.0115],\n [0.2033],\n [0.1327],\n [0.0180],\n [0.0610],\n [0.2927],\n [0.1182],\n [0.0115],\n [0.4474],\n [0.3513],\n [0.0451],\n [0.4089],\n [0.0375],\n [0.0127],\n [0.0630],\n [0.0428],\n [0.2085],\n [0.0529],\n [0.3436],\n [0.0678],\n [0.0717],\n [0.0799],\n [0.0967],\n [0.1246],\n [0.1086],\n [0.0387],\n [0.1742],\n [0.1582],\n [0.1374],\n [0.4205],\n [0.0534],\n [0.3051],\n [0.1204],\n [0.0423],\n [0.0324],\n [0.0141],\n [0.0312],\n [0.0261],\n [0.2619],\n [0.0767],\n [0.1742],\n [0.0311],\n [0.1763],\n [0.0326],\n [0.0529],\n [0.3928],\n [0.1209],\n [0.0724],\n [0.3551],\n [0.2067],\n [0.0288],\n [0.0782],\n [0.0661],\n [0.0469],\n [0.1089],\n [0.0985],\n [0.1032],\n [0.1083],\n [0.0546],\n [0.0983],\n [0.1302],\n [0.0153],\n [0.2179],\n [0.1196],\n [0.0275],\n [0.4366],\n [0.0340],\n [0.0286],\n [0.1193],\n [0.0729],\n [0.0553],\n [0.0159],\n [0.0140],\n [0.2195],\n [0.3792],\n [0.3966],\n [0.0424],\n [0.0872],\n [0.0687],\n [0.1941],\n [0.0179],\n [0.0380],\n [0.2445],\n [0.1905],\n [0.1518],\n [0.2370],\n [0.0706],\n [0.1668],\n [0.1265],\n [0.2363],\n [0.0354],\n [0.0263],\n [0.0653],\n [0.0097],\n [0.0152],\n [0.0495],\n [0.2952],\n [0.3581],\n [0.0388],\n [0.0365],\n [0.2808],\n [0.0189],\n [0.0133],\n [0.0692],\n [0.0256],\n [0.0500],\n [0.1452],\n [0.3315],\n [0.4509],\n [0.2079],\n [0.0140],\n [0.2505],\n [0.1044],\n [0.0121],\n [0.0087],\n [0.0453],\n [0.0173],\n [0.0127],\n [0.0176],\n [0.3826],\n [0.0843],\n [0.0885],\n [0.0133],\n [0.0190],\n [0.0278],\n [0.0612],\n [0.2574],\n [0.0404],\n [0.0735],\n [0.0527],\n [0.0300],\n [0.1384],\n [0.2189],\n [0.0301],\n [0.2303],\n [0.0425],\n [0.0294],\n [0.0103],\n [0.2857],\n [0.0620],\n [0.0938],\n [0.2283],\n [0.0237],\n [0.1175],\n [0.1809],\n [0.0725],\n [0.0107],\n [0.0629],\n [0.4485],\n [0.0233],\n [0.0165],\n [0.2240],\n [0.1200],\n [0.0665],\n [0.1153],\n [0.2957],\n [0.0112],\n [0.0328],\n [0.2823],\n [0.4248],\n [0.0308],\n [0.0216],\n [0.1206],\n [0.2086],\n [0.0115],\n [0.0399],\n [0.0246],\n [0.3960],\n [0.1782],\n [0.0591],\n [0.0092],\n [0.0600],\n [0.2938],\n [0.1144],\n [0.0136],\n [0.2075],\n [0.0426],\n [0.0998],\n [0.0407],\n [0.2944],\n [0.2721],\n [0.0734],\n [0.2927],\n [0.0482],\n [0.2740],\n [0.0363],\n [0.4624],\n [0.0558],\n [0.1669],\n [0.0243],\n [0.0109],\n [0.1209],\n [0.0617],\n [0.0634],\n [0.0183],\n [0.0319],\n [0.1135],\n [0.0121],\n [0.0314],\n [0.0137],\n [0.0195],\n [0.0094],\n [0.3304],\n [0.0694],\n [0.0144],\n [0.0278],\n [0.1393],\n [0.3971],\n [0.0939],\n [0.0489],\n [0.0763],\n [0.0394],\n [0.2953],\n [0.0581],\n [0.0404],\n [0.0489],\n [0.0429],\n [0.1940],\n [0.0098],\n [0.0535],\n [0.2953],\n [0.2188],\n [0.0115],\n [0.1468],\n [0.0210],\n [0.2410],\n [0.0685],\n [0.1935],\n [0.1258],\n [0.0146],\n [0.0279],\n [0.0240],\n [0.3981],\n [0.2131],\n [0.0267],\n [0.0184],\n [0.2806],\n [0.2224],\n [0.2687],\n [0.0207],\n [0.2931],\n [0.0707],\n [0.0408],\n [0.0836],\n [0.0799],\n [0.1043],\n [0.0235],\n [0.1093],\n [0.0915],\n [0.0186],\n [0.0885],\n [0.0143],\n [0.0430],\n [0.4653],\n [0.1440],\n [0.0343],\n [0.1683],\n [0.0222],\n [0.1450],\n [0.0497],\n [0.2624],\n [0.0158],\n [0.0157],\n [0.3439],\n [0.1724],\n [0.1858],\n [0.4211],\n [0.0741],\n [0.0708],\n [0.0437],\n [0.0117],\n [0.1091],\n [0.0450],\n [0.1210],\n [0.0864],\n [0.1131],\n [0.0796],\n [0.3588],\n [0.1135],\n [0.0211],\n [0.0152],\n [0.0109],\n [0.1337],\n [0.0341],\n [0.1293],\n [0.0809],\n [0.1133],\n [0.0163],\n [0.0598],\n [0.1512],\n [0.0480],\n [0.1759],\n [0.1126],\n [0.1127],\n [0.0263],\n [0.0215],\n [0.4364],\n [0.0164],\n [0.0447],\n [0.0979],\n [0.0678],\n [0.0624],\n [0.0317],\n [0.0102],\n [0.0188],\n [0.0698],\n [0.1521],\n [0.0642],\n [0.3642],\n [0.4675],\n [0.0807],\n [0.0191],\n [0.0761],\n [0.0902],\n [0.2640],\n [0.0658],\n [0.0115],\n [0.0166],\n [0.0222],\n [0.0138],\n [0.0588],\n [0.0254],\n [0.3206],\n [0.0467],\n [0.0861],\n [0.0161],\n [0.0726],\n [0.2488],\n [0.0441],\n [0.0508],\n [0.2247],\n [0.2302],\n [0.1532],\n [0.4200],\n [0.0451],\n [0.3172],\n [0.3833],\n [0.1273],\n [0.0189],\n [0.0763],\n [0.2182],\n [0.0644],\n [0.2589],\n [0.1022],\n [0.0138],\n [0.0616],\n [0.2501],\n [0.0143],\n [0.0120],\n [0.3911],\n [0.2098],\n [0.1860],\n [0.0638],\n [0.0235],\n [0.0264],\n [0.1376],\n [0.3966],\n [0.2488],\n [0.1522],\n [0.0390],\n [0.3700],\n [0.1037],\n [0.0729],\n [0.1019],\n [0.0281],\n [0.0292],\n [0.0099],\n [0.2580],\n [0.0105],\n [0.1386],\n [0.0141],\n [0.0188],\n [0.0625],\n [0.2696],\n [0.0582],\n [0.0218],\n [0.1327],\n [0.0290],\n [0.3961],\n [0.0202],\n [0.0209],\n [0.3187],\n [0.1900],\n [0.0237],\n [0.3660],\n [0.1311],\n [0.0300],\n [0.0211],\n [0.4100],\n [0.0311],\n [0.1034],\n [0.4346],\n [0.1150],\n [0.0588],\n [0.1075],\n [0.0989],\n [0.2195],\n [0.4500],\n [0.0934],\n [0.0930],\n [0.1336],\n [0.1932],\n [0.1717],\n [0.0731],\n [0.1601],\n [0.2492],\n [0.0096],\n [0.0759],\n [0.1010],\n [0.0592],\n [0.4519],\n [0.2835],\n [0.0693],\n [0.1462],\n [0.0280],\n [0.4231],\n [0.0400],\n [0.1261],\n [0.0129],\n [0.1344],\n [0.0724],\n [0.0362],\n [0.0444],\n [0.0724],\n [0.0266],\n [0.0624],\n [0.0094],\n [0.0557],\n [0.1328],\n [0.1478],\n [0.1098],\n [0.0486],\n [0.1091],\n [0.1119],\n [0.1213],\n [0.2821],\n [0.4471],\n [0.0485],\n [0.0278],\n [0.2685],\n [0.0907],\n [0.0253],\n [0.0618],\n [0.0361],\n [0.2087],\n [0.1609],\n [0.2896],\n [0.2296],\n [0.1015],\n [0.2034],\n [0.0103],\n [0.0483],\n [0.0843],\n [0.2846],\n [0.0126],\n [0.0839],\n [0.0097],\n [0.3067],\n [0.0319],\n [0.1666],\n [0.0134],\n [0.3563],\n [0.0354],\n [0.2181],\n [0.0399],\n [0.1233],\n [0.0332],\n [0.1251],\n [0.3705],\n [0.0720],\n [0.0260],\n [0.2191],\n [0.0998],\n [0.2293],\n [0.1474],\n [0.0092],\n [0.0092],\n [0.0433],\n [0.1093],\n [0.0165],\n [0.3294],\n [0.0136],\n [0.0735],\n [0.0381],\n [0.1373],\n [0.1616],\n [0.0496],\n [0.1992],\n [0.0342],\n [0.2832],\n [0.0306],\n [0.0188],\n [0.3583],\n [0.1543],\n [0.0188],\n [0.0111],\n [0.0964],\n [0.0963],\n [0.2209],\n [0.1034],\n [0.1088],\n [0.0695],\n [0.0308],\n [0.0280],\n [0.0712],\n [0.0474],\n [0.1890],\n [0.3057],\n [0.0896],\n [0.2190],\n [0.1548],\n [0.4623],\n [0.4395],\n [0.3971],\n [0.0328],\n [0.0132],\n [0.4267],\n [0.0234],\n [0.0202],\n [0.0141],\n [0.1102],\n [0.0159],\n [0.0842],\n [0.0629],\n [0.1334],\n [0.1256],\n [0.2835],\n [0.3958],\n [0.1798],\n [0.0108],\n [0.0144],\n [0.0220],\n [0.0982],\n [0.1031],\n [0.0454],\n [0.0292],\n [0.1306],\n [0.4508],\n [0.0465],\n [0.3683],\n [0.0549],\n [0.0102],\n [0.0222],\n [0.0503],\n [0.0245],\n [0.1466],\n [0.1999],\n [0.0237],\n [0.1147],\n [0.4205],\n [0.0654],\n [0.1033],\n [0.1182],\n [0.0737],\n [0.0561],\n [0.2595],\n [0.0116],\n [0.1922],\n [0.4246],\n [0.3039],\n [0.1907],\n [0.4135],\n [0.3967],\n [0.2716],\n [0.2395],\n [0.2179],\n [0.2798],\n [0.0185],\n [0.0197],\n [0.0482],\n [0.0086],\n [0.0088],\n [0.1054],\n [0.1191],\n [0.0319],\n [0.1223],\n [0.0358],\n [0.2026],\n [0.0206],\n [0.0784],\n [0.1204],\n [0.3416],\n [0.3174],\n [0.0210],\n [0.0305],\n [0.0098],\n [0.3320],\n [0.0258],\n [0.3058],\n [0.3179],\n [0.1205],\n [0.0276],\n [0.0308],\n [0.0135],\n [0.3972],\n [0.2718],\n [0.4641],\n [0.0432],\n [0.0744],\n [0.3558],\n [0.2100],\n [0.1327],\n [0.1907],\n [0.0276],\n [0.1947],\n [0.0844],\n [0.2688],\n [0.0658],\n [0.0929],\n [0.1471],\n [0.1222],\n [0.0212],\n [0.0804],\n [0.4366],\n [0.2472],\n [0.0325],\n [0.0178],\n [0.3040],\n [0.0868],\n [0.0683],\n [0.0470],\n [0.2027],\n [0.0262],\n [0.1257],\n [0.1146],\n [0.0586],\n [0.1017],\n [0.4349],\n [0.0286],\n [0.0723],\n [0.3070],\n [0.0135],\n [0.0380],\n [0.0447],\n [0.0161],\n [0.0729],\n [0.0360],\n [0.1328],\n [0.0126],\n [0.0531],\n [0.1831],\n [0.4434],\n [0.0198],\n [0.0878],\n [0.0382],\n [0.0387],\n [0.0438],\n [0.0720],\n [0.0311],\n [0.1378],\n [0.1178],\n [0.1888],\n [0.1199],\n [0.2023],\n [0.1153],\n [0.0523],\n [0.0420],\n [0.0200],\n [0.1671],\n [0.1086],\n [0.0503],\n [0.0441],\n [0.0242],\n [0.1676],\n [0.0120],\n [0.4497],\n [0.0396],\n [0.0922],\n [0.2931],\n [0.0194],\n [0.0267],\n [0.1875],\n [0.1045],\n [0.0839],\n [0.1251],\n [0.0294],\n [0.1090],\n [0.0136],\n [0.0851],\n [0.0360],\n [0.0158],\n [0.0944],\n [0.0110],\n [0.0114],\n [0.0586],\n [0.4468],\n [0.0760],\n [0.0501],\n [0.2267],\n [0.0528],\n [0.0367],\n [0.0803],\n [0.1456],\n [0.2818],\n [0.0266],\n [0.1995],\n [0.3691],\n [0.2341],\n [0.2593],\n [0.0636],\n [0.1788],\n [0.0479],\n [0.0509],\n [0.1104],\n [0.0918],\n [0.1508],\n [0.3680],\n [0.3948],\n [0.1899],\n [0.2569],\n [0.0363],\n [0.0262],\n [0.0936],\n [0.0550],\n [0.1027],\n [0.1444],\n [0.0330],\n [0.0097],\n [0.0761],\n [0.2207],\n [0.0326],\n [0.2501],\n [0.0394],\n [0.0760],\n [0.0381],\n [0.0115],\n [0.2717],\n [0.0423],\n [0.0731],\n [0.1560],\n [0.0826],\n [0.0092],\n [0.0219],\n [0.0751],\n [0.1322],\n [0.2677],\n [0.1361],\n [0.4089],\n [0.0925],\n [0.0266],\n [0.1068],\n [0.3935],\n [0.0987],\n [0.0115],\n [0.3348],\n [0.0551],\n [0.0817],\n [0.0489],\n [0.1392],\n [0.0596],\n [0.0844],\n [0.2388],\n [0.0960],\n [0.0721],\n [0.1400],\n [0.4667],\n [0.2374],\n [0.0349],\n [0.0857],\n [0.1599],\n [0.1922],\n [0.0281],\n [0.0183],\n [0.4507],\n [0.0167],\n [0.0283],\n [0.0402],\n [0.2076],\n [0.1693],\n [0.1446],\n [0.3547],\n [0.0943],\n [0.3730],\n [0.1823],\n [0.0426],\n [0.0149],\n [0.0327],\n [0.3715],\n [0.0474],\n [0.1343],\n [0.1915],\n [0.0690],\n [0.0092],\n [0.1643],\n [0.2189],\n [0.3149],\n [0.2171],\n [0.2178],\n [0.0097],\n [0.3628],\n [0.0163],\n [0.0684],\n [0.1145],\n [0.4074],\n [0.0514],\n [0.3587],\n [0.0905],\n [0.0159],\n [0.1992],\n [0.0109]])\n" + "predicted Y value: tensor([[0.0089],\n [0.0051],\n [0.1535],\n [0.1008],\n [0.0365],\n [0.0014],\n [0.1275],\n [0.0172],\n [0.1439],\n [0.0088],\n [0.0013],\n [0.3466],\n [0.0078],\n [0.0303],\n [0.0024],\n [0.0607],\n [0.0556],\n [0.0826],\n [0.0765],\n [0.0027],\n [0.0869],\n [0.0424],\n [0.0013],\n [0.1338],\n [0.0017],\n [0.0020],\n [0.0009],\n [0.0014],\n [0.0090],\n [0.4073],\n [0.0026],\n [0.0009],\n [0.0141],\n [0.0897],\n [0.3593],\n [0.3849],\n [0.0073],\n [0.0204],\n [0.1406],\n [0.0053],\n [0.3840],\n [0.0802],\n [0.0068],\n [0.0190],\n [0.3849],\n [0.0034],\n [0.0045],\n [0.3272],\n [0.0397],\n [0.3087],\n [0.0162],\n [0.0159],\n [0.0033],\n [0.0559],\n [0.0238],\n [0.0073],\n [0.0113],\n [0.0102],\n [0.3827],\n [0.0359],\n [0.0138],\n [0.0248],\n [0.0080],\n [0.1858],\n [0.0766],\n [0.0123],\n [0.0077],\n [0.0042],\n [0.0908],\n [0.4172],\n [0.0010],\n [0.1105],\n [0.0463],\n [0.1457],\n [0.0078],\n [0.0821],\n [0.0011],\n [0.0210],\n [0.0273],\n [0.0248],\n [0.0082],\n [0.0007],\n [0.0022],\n [0.2436],\n [0.0297],\n [0.0235],\n [0.0168],\n [0.0053],\n [0.0128],\n [0.0156],\n [0.0009],\n [0.0375],\n [0.0008],\n [0.0645],\n [0.0750],\n [0.0055],\n [0.0185],\n [0.0008],\n [0.0082],\n [0.0138],\n [0.2082],\n [0.1823],\n [0.0027],\n [0.0124],\n [0.0010],\n [0.0187],\n [0.2454],\n [0.0019],\n [0.1413],\n [0.0010],\n [0.0050],\n [0.0020],\n [0.0011],\n [0.2266],\n [0.0545],\n [0.0164],\n [0.0678],\n [0.0012],\n [0.0271],\n [0.0009],\n [0.0029],\n [0.0058],\n [0.0009],\n [0.0762],\n [0.0013],\n [0.0276],\n [0.3940],\n [0.4213],\n [0.0041],\n [0.0144],\n [0.1491],\n [0.0011],\n [0.0077],\n [0.0032],\n [0.3155],\n [0.0009],\n [0.0072],\n [0.0056],\n [0.3580],\n [0.3235],\n [0.0130],\n [0.4032],\n [0.0405],\n [0.2882],\n [0.0045],\n [0.0041],\n [0.0026],\n [0.0354],\n [0.0094],\n [0.0278],\n [0.0011],\n [0.0036],\n [0.2996],\n [0.0652],\n [0.4247],\n [0.0048],\n [0.0016],\n [0.0703],\n [0.3676],\n [0.0231],\n [0.0206],\n [0.0093],\n [0.0087],\n [0.0649],\n [0.0207],\n [0.0010],\n [0.0076],\n [0.3366],\n [0.0015],\n [0.0034],\n [0.2819],\n [0.0007],\n [0.0024],\n [0.0015],\n [0.1623],\n [0.0838],\n [0.0431],\n [0.2744],\n [0.1369],\n [0.0007],\n [0.0022],\n [0.2049],\n [0.0010],\n [0.1057],\n [0.0503],\n [0.0021],\n [0.0136],\n [0.1939],\n [0.0401],\n [0.0010],\n [0.4003],\n [0.2621],\n [0.0087],\n [0.3507],\n [0.0061],\n [0.0012],\n [0.0103],\n [0.0080],\n [0.1068],\n [0.0098],\n [0.2625],\n [0.0162],\n [0.0178],\n [0.0215],\n [0.0283],\n [0.0444],\n [0.0356],\n [0.0037],\n [0.0779],\n [0.0652],\n [0.0521],\n [0.3626],\n [0.0116],\n [0.2099],\n [0.0431],\n [0.0076],\n [0.0050],\n [0.0010],\n [0.0049],\n [0.0036],\n [0.1638],\n [0.0205],\n [0.0775],\n [0.0026],\n [0.0826],\n [0.0052],\n [0.0111],\n [0.3208],\n [0.0435],\n [0.0140],\n [0.2729],\n [0.1035],\n [0.0041],\n [0.0202],\n [0.0164],\n [0.0089],\n [0.0359],\n [0.0306],\n [0.0325],\n [0.0354],\n [0.0096],\n [0.0304],\n [0.0473],\n [0.0016],\n [0.1147],\n [0.0368],\n [0.0034],\n [0.3918],\n [0.0054],\n [0.0040],\n [0.0415],\n [0.0190],\n [0.0116],\n [0.0014],\n [0.0010],\n [0.1187],\n [0.3011],\n [0.3357],\n [0.0077],\n [0.0243],\n [0.0128],\n [0.0978],\n [0.0020],\n [0.0064],\n [0.1374],\n [0.0916],\n [0.0623],\n [0.1318],\n [0.0144],\n [0.0737],\n [0.0468],\n [0.1312],\n [0.0056],\n [0.0017],\n [0.0157],\n [0.0008],\n [0.0016],\n [0.0098],\n [0.2015],\n [0.2831],\n [0.0054],\n [0.0062],\n [0.1790],\n [0.0022],\n [0.0012],\n [0.0174],\n [0.0033],\n [0.0100],\n [0.0580],\n [0.2458],\n [0.4155],\n [0.1052],\n [0.0007],\n [0.1498],\n [0.0344],\n [0.0011],\n [0.0006],\n [0.0088],\n [0.0018],\n [0.0011],\n [0.0014],\n [0.3143],\n [0.0236],\n [0.0252],\n [0.0010],\n [0.0022],\n [0.0041],\n [0.0105],\n [0.1520],\n [0.0063],\n [0.0197],\n [0.0082],\n [0.0038],\n [0.0533],\n [0.1163],\n [0.0032],\n [0.1304],\n [0.0058],\n [0.0045],\n [0.0008],\n [0.1758],\n [0.0078],\n [0.0282],\n [0.1256],\n [0.0021],\n [0.0388],\n [0.0826],\n [0.0185],\n [0.0009],\n [0.0152],\n [0.4050],\n [0.0030],\n [0.0017],\n [0.1281],\n [0.0424],\n [0.0090],\n [0.0404],\n [0.2027],\n [0.0005],\n [0.0053],\n [0.1841],\n [0.3782],\n [0.0047],\n [0.0025],\n [0.0432],\n [0.1070],\n [0.0010],\n [0.0069],\n [0.0033],\n [0.3327],\n [0.0852],\n [0.0135],\n [0.0007],\n [0.0109],\n [0.1961],\n [0.0393],\n [0.0013],\n [0.1051],\n [0.0078],\n [0.0324],\n [0.0065],\n [0.1976],\n [0.1738],\n [0.0195],\n [0.1941],\n [0.0088],\n [0.1793],\n [0.0061],\n [0.4261],\n [0.0122],\n [0.0733],\n [0.0026],\n [0.0009],\n [0.0436],\n [0.0141],\n [0.0124],\n [0.0020],\n [0.0048],\n [0.0381],\n [0.0009],\n [0.0044],\n [0.0014],\n [0.0010],\n [0.0008],\n [0.2416],\n [0.0177],\n [0.0015],\n [0.0041],\n [0.0554],\n [0.3380],\n [0.0284],\n [0.0093],\n [0.0200],\n [0.0057],\n [0.2006],\n [0.0126],\n [0.0063],\n [0.0072],\n [0.0071],\n [0.0981],\n [0.0008],\n [0.0116],\n [0.1803],\n [0.1175],\n [0.0010],\n [0.0610],\n [0.0026],\n [0.1416],\n [0.0168],\n [0.0973],\n [0.0457],\n [0.0012],\n [0.0016],\n [0.0015],\n [0.3407],\n [0.1155],\n [0.0035],\n [0.0010],\n [0.1799],\n [0.1241],\n [0.1657],\n [0.0018],\n [0.1940],\n [0.0171],\n [0.0075],\n [0.0230],\n [0.0113],\n [0.0342],\n [0.0031],\n [0.0369],\n [0.0262],\n [0.0018],\n [0.0224],\n [0.0014],\n [0.0081],\n [0.4363],\n [0.0562],\n [0.0056],\n [0.0754],\n [0.0028],\n [0.0582],\n [0.0100],\n [0.1473],\n [0.0016],\n [0.0013],\n [0.2620],\n [0.0646],\n [0.0910],\n [0.3646],\n [0.0181],\n [0.0146],\n [0.0076],\n [0.0009],\n [0.0363],\n [0.0086],\n [0.0336],\n [0.0206],\n [0.0374],\n [0.0212],\n [0.2859],\n [0.0384],\n [0.0026],\n [0.0016],\n [0.0009],\n [0.0519],\n [0.0054],\n [0.0392],\n [0.0225],\n [0.0382],\n [0.0016],\n [0.0075],\n [0.0619],\n [0.0040],\n [0.0810],\n [0.0372],\n [0.0376],\n [0.0037],\n [0.0028],\n [0.3910],\n [0.0017],\n [0.0084],\n [0.0298],\n [0.0160],\n [0.0112],\n [0.0024],\n [0.0008],\n [0.0019],\n [0.0181],\n [0.0624],\n [0.0127],\n [0.2768],\n [0.4461],\n [0.0224],\n [0.0015],\n [0.0200],\n [0.0274],\n [0.1512],\n [0.0161],\n [0.0005],\n [0.0009],\n [0.0028],\n [0.0012],\n [0.0132],\n [0.0028],\n [0.2346],\n [0.0088],\n [0.0227],\n [0.0015],\n [0.0187],\n [0.1476],\n [0.0069],\n [0.0096],\n [0.1176],\n [0.1304],\n [0.0643],\n [0.3622],\n [0.0078],\n [0.2245],\n [0.3165],\n [0.0477],\n [0.0022],\n [0.0203],\n [0.1160],\n [0.0148],\n [0.1549],\n [0.0316],\n [0.0011],\n [0.0141],\n [0.1498],\n [0.0011],\n [0.0011],\n [0.3146],\n [0.1083],\n [0.0908],\n [0.0128],\n [0.0031],\n [0.0038],\n [0.0525],\n [0.3349],\n [0.1460],\n [0.0631],\n [0.0054],\n [0.2970],\n [0.0336],\n [0.0166],\n [0.0312],\n [0.0037],\n [0.0038],\n [0.0008],\n [0.1529],\n [0.0008],\n [0.0544],\n [0.0013],\n [0.0021],\n [0.0079],\n [0.1678],\n [0.0127],\n [0.0026],\n [0.0506],\n [0.0042],\n [0.3334],\n [0.0022],\n [0.0021],\n [0.2290],\n [0.0904],\n [0.0032],\n [0.2832],\n [0.0484],\n [0.0022],\n [0.0026],\n [0.3545],\n [0.0048],\n [0.0331],\n [0.3835],\n [0.0400],\n [0.0132],\n [0.0342],\n [0.0311],\n [0.1180],\n [0.4113],\n [0.0278],\n [0.0277],\n [0.0400],\n [0.0968],\n [0.0736],\n [0.0176],\n [0.0696],\n [0.1483],\n [0.0007],\n [0.0197],\n [0.0305],\n [0.0125],\n [0.4180],\n [0.1870],\n [0.0174],\n [0.0603],\n [0.0042],\n [0.3729],\n [0.0069],\n [0.0466],\n [0.0006],\n [0.0530],\n [0.0183],\n [0.0061],\n [0.0061],\n [0.0185],\n [0.0021],\n [0.0099],\n [0.0007],\n [0.0121],\n [0.0504],\n [0.0619],\n [0.0373],\n [0.0078],\n [0.0366],\n [0.0357],\n [0.0443],\n [0.1825],\n [0.3996],\n [0.0054],\n [0.0040],\n [0.1632],\n [0.0247],\n [0.0019],\n [0.0141],\n [0.0060],\n [0.1078],\n [0.0698],\n [0.1844],\n [0.1288],\n [0.0308],\n [0.1057],\n [0.0009],\n [0.0100],\n [0.0234],\n [0.1900],\n [0.0010],\n [0.0231],\n [0.0007],\n [0.2147],\n [0.0048],\n [0.0733],\n [0.0012],\n [0.2775],\n [0.0033],\n [0.1134],\n [0.0070],\n [0.0424],\n [0.0055],\n [0.0451],\n [0.2994],\n [0.0181],\n [0.0035],\n [0.1174],\n [0.0287],\n [0.1288],\n [0.0613],\n [0.0007],\n [0.0007],\n [0.0083],\n [0.0365],\n [0.0017],\n [0.2397],\n [0.0007],\n [0.0196],\n [0.0065],\n [0.0519],\n [0.0722],\n [0.0098],\n [0.0986],\n [0.0025],\n [0.1867],\n [0.0046],\n [0.0015],\n [0.2836],\n [0.0665],\n [0.0021],\n [0.0005],\n [0.0285],\n [0.0281],\n [0.1217],\n [0.0330],\n [0.0361],\n [0.0177],\n [0.0046],\n [0.0041],\n [0.0175],\n [0.0092],\n [0.0877],\n [0.2109],\n [0.0267],\n [0.1180],\n [0.0670],\n [0.4255],\n [0.4027],\n [0.3366],\n [0.0052],\n [0.0009],\n [0.3857],\n [0.0031],\n [0.0013],\n [0.0011],\n [0.0379],\n [0.0017],\n [0.0236],\n [0.0153],\n [0.0518],\n [0.0456],\n [0.1873],\n [0.3320],\n [0.0881],\n [0.0009],\n [0.0015],\n [0.0027],\n [0.0304],\n [0.0332],\n [0.0036],\n [0.0043],\n [0.0409],\n [0.4144],\n [0.0087],\n [0.2914],\n [0.0116],\n [0.0008],\n [0.0028],\n [0.0103],\n [0.0032],\n [0.0606],\n [0.1001],\n [0.0028],\n [0.0397],\n [0.3626],\n [0.0158],\n [0.0331],\n [0.0401],\n [0.0182],\n [0.0125],\n [0.1572],\n [0.0010],\n [0.0937],\n [0.3776],\n [0.2067],\n [0.0914],\n [0.3666],\n [0.3347],\n [0.1722],\n [0.1384],\n [0.1152],\n [0.1753],\n [0.0009],\n [0.0023],\n [0.0088],\n [0.0006],\n [0.0006],\n [0.0313],\n [0.0413],\n [0.0022],\n [0.0413],\n [0.0059],\n [0.1054],\n [0.0024],\n [0.0173],\n [0.0426],\n [0.2546],\n [0.2232],\n [0.0026],\n [0.0045],\n [0.0008],\n [0.2471],\n [0.0035],\n [0.2115],\n [0.2262],\n [0.0433],\n [0.0039],\n [0.0047],\n [0.0013],\n [0.3367],\n [0.1733],\n [0.4315],\n [0.0075],\n [0.0182],\n [0.2763],\n [0.1106],\n [0.0510],\n [0.0907],\n [0.0039],\n [0.0987],\n [0.0239],\n [0.1644],\n [0.0162],\n [0.0271],\n [0.0608],\n [0.0351],\n [0.0014],\n [0.0221],\n [0.3912],\n [0.1440],\n [0.0051],\n [0.0015],\n [0.2073],\n [0.0235],\n [0.0168],\n [0.0090],\n [0.1056],\n [0.0036],\n [0.0452],\n [0.0396],\n [0.0070],\n [0.0314],\n [0.3853],\n [0.0039],\n [0.0184],\n [0.2150],\n [0.0013],\n [0.0055],\n [0.0084],\n [0.0015],\n [0.0190],\n [0.0060],\n [0.0507],\n [0.0007],\n [0.0113],\n [0.0851],\n [0.3850],\n [0.0012],\n [0.0245],\n [0.0066],\n [0.0069],\n [0.0040],\n [0.0183],\n [0.0043],\n [0.0529],\n [0.0398],\n [0.0887],\n [0.0426],\n [0.0927],\n [0.0404],\n [0.0049],\n [0.0056],\n [0.0024],\n [0.0739],\n [0.0359],\n [0.0104],\n [0.0081],\n [0.0023],\n [0.0747],\n [0.0011],\n [0.4100],\n [0.0068],\n [0.0268],\n [0.1948],\n [0.0013],\n [0.0018],\n [0.0867],\n [0.0346],\n [0.0231],\n [0.0455],\n [0.0044],\n [0.0365],\n [0.0013],\n [0.0245],\n [0.0059],\n [0.0014],\n [0.0257],\n [0.0010],\n [0.0010],\n [0.0131],\n [0.3990],\n [0.0200],\n [0.0078],\n [0.1217],\n [0.0110],\n [0.0064],\n [0.0219],\n [0.0580],\n [0.1824],\n [0.0020],\n [0.0986],\n [0.2947],\n [0.1087],\n [0.1563],\n [0.0122],\n [0.0784],\n [0.0097],\n [0.0097],\n [0.0347],\n [0.0263],\n [0.0613],\n [0.2907],\n [0.3285],\n [0.0896],\n [0.1502],\n [0.0061],\n [0.0037],\n [0.0282],\n [0.0116],\n [0.0323],\n [0.0576],\n [0.0054],\n [0.0008],\n [0.0200],\n [0.1212],\n [0.0052],\n [0.1496],\n [0.0065],\n [0.0199],\n [0.0065],\n [0.0010],\n [0.1536],\n [0.0076],\n [0.0191],\n [0.0691],\n [0.0187],\n [0.0007],\n [0.0027],\n [0.0162],\n [0.0440],\n [0.1624],\n [0.0502],\n [0.3496],\n [0.0270],\n [0.0034],\n [0.0337],\n [0.3247],\n [0.0274],\n [0.0010],\n [0.2565],\n [0.0099],\n [0.0126],\n [0.0092],\n [0.0546],\n [0.0139],\n [0.0238],\n [0.1364],\n [0.0246],\n [0.0183],\n [0.0558],\n [0.4423],\n [0.1326],\n [0.0059],\n [0.0229],\n [0.0692],\n [0.0944],\n [0.0022],\n [0.0017],\n [0.4130],\n [0.0013],\n [0.0037],\n [0.0071],\n [0.1049],\n [0.0774],\n [0.0569],\n [0.2711],\n [0.0290],\n [0.3081],\n [0.0848],\n [0.0078],\n [0.0015],\n [0.0046],\n [0.3030],\n [0.0093],\n [0.0481],\n [0.0931],\n [0.0174],\n [0.0007],\n [0.0695],\n [0.1172],\n [0.2178],\n [0.1137],\n [0.1141],\n [0.0008],\n [0.2754],\n [0.0008],\n [0.0167],\n [0.0398],\n [0.3444],\n [0.0089],\n [0.2858],\n [0.0251],\n [0.0016],\n [0.0993],\n [0.0009]])\n" ] } ], @@ -248,7 +183,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 87, "metadata": {}, "outputs": [ { @@ -265,7 +200,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 83, "metadata": {}, "outputs": [], "source": [ diff --git a/pytorch/Dockerfile b/pytorch-training-eval/Dockerfile similarity index 66% rename from pytorch/Dockerfile rename to pytorch-training-eval/Dockerfile index ee2303f..a24073b 100644 --- a/pytorch/Dockerfile +++ b/pytorch-training-eval/Dockerfile @@ -1,10 +1,11 @@ FROM ubuntu:latest -RUN apt-get update && apt-get install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn && rm -rf /var/lib/apt/lists/* +RUN apt-get update && apt-get install -y python3-pip && pip3 install setuptools && pip3 install numpy && pip3 install pandas && pip3 install wget && pip3 install scikit-learn && pip3 install matplotlib && rm -rf /var/lib/apt/lists/* RUN pip3 install torch torchvision torchaudio WORKDIR /app COPY ./create.py ./ COPY ./stats.py ./ COPY ./stroke-pytorch.py ./ +COPY ./stroke-pytorch-eval.py ./ diff --git a/pytorch-training-eval/Jenkinsfile-eval b/pytorch-training-eval/Jenkinsfile-eval new file mode 100644 index 0000000..7dcde6a --- /dev/null +++ b/pytorch-training-eval/Jenkinsfile-eval @@ -0,0 +1,32 @@ +pipeline { + agent { + dockerfile true + } + stages { + stage('checkout') { + steps { + git 'https://git.wmi.amu.edu.pl/s434766/ium_434766.git' + copyArtifacts fingerprintArtifacts: true, projectName: 's434766-create-dataset' + copyArtifacts fingerprintArtifacts: true, projectName: 's434766-training' + } + } + stage('Docker'){ + steps{ + sh 'python3 "./stroke-pytorch-eval.py" >> eval.txt' + } + } + stage('archiveArtifacts') { + steps { + archiveArtifacts 'eval.txt' + + } + post { + success { + emailext body: 'Evaluation of stroke predictions is finished', + subject: 's434766 evaluation finished', + to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms' + } + } + } + } +} \ No newline at end of file diff --git a/pytorch/Jenkinsfile b/pytorch-training-eval/Jenkinsfile-train similarity index 51% rename from pytorch/Jenkinsfile rename to pytorch-training-eval/Jenkinsfile-train index 3d40259..de23eb8 100644 --- a/pytorch/Jenkinsfile +++ b/pytorch-training-eval/Jenkinsfile-train @@ -11,19 +11,21 @@ pipeline { } stage('Docker'){ steps{ - sh 'python3 "./stroke-pytorch.py" > model.txt' - } - } - stage('checkout: Check out from version control') { - steps { - git 'https://git.wmi.amu.edu.pl/s434766/ium_434766.git' + sh 'python3 "./stroke-pytorch.py" ${BATCH_SIZE} ${EPOCHS} > pred.txt' } } stage('archiveArtifacts') { steps { - archiveArtifacts 'model.txt' + archiveArtifacts 'pred.txt' archiveArtifacts 'stroke.pkl' } + post { + success { + emailext body: 'Training of stroke predictions is finished', + subject: 's434766 training finished', + to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms' + } + } } } } \ No newline at end of file diff --git a/stroke-pytorch-eval.py b/stroke-pytorch-eval.py new file mode 100644 index 0000000..9c28356 --- /dev/null +++ b/stroke-pytorch-eval.py @@ -0,0 +1,50 @@ +import torch +import torch.nn as nn +import numpy as np +from os import path +import torch.nn.functional as F +from torch import nn +from torch.autograd import Variable +import torchvision.transforms as transforms +import pandas as pd +from sklearn.metrics import accuracy_score +from sklearn.metrics import mean_squared_error +from sklearn.metrics import classification_report +import matplotlib.pyplot as plt + +class LogisticRegressionModel(nn.Module): + def __init__(self, input_dim, output_dim): + super(LogisticRegressionModel, self).__init__() + self.linear = nn.Linear(input_dim, output_dim) + self.sigmoid = nn.Sigmoid() + def forward(self, x): + out = self.linear(x) + return self.sigmoid(out) + +np.set_printoptions(suppress=False) + +data_test = pd.read_csv("data_test.csv") + +FEATURES = ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi'] + + +x_test = data_test[FEATURES].astype(np.float32) +y_test = data_test['stroke'].astype(np.float32) + +fTest= torch.from_numpy(x_test.values) +tTest = torch.from_numpy(y_test.values) + +model = LogisticRegressionModel(6,1) +model.load_state_dict(torch.load('stroke.pth')) +y_pred = model(fTest) + +rmse = mean_squared_error(tTest, y_pred.detach().numpy()) +acc = accuracy_score(tTest, np.argmax(y_pred.detach().numpy(), axis=1)) +print('-' * 60) +print(classification_report(tTest, y_pred.detach().numpy().round())) +print(f" RMSE: {rmse}") +print(f" Accuracy: {acc}") +print('-' * 60) + + + diff --git a/stroke-pytorch.py b/stroke-pytorch.py index 4f9ad31..93b33af 100644 --- a/stroke-pytorch.py +++ b/stroke-pytorch.py @@ -1,4 +1,5 @@ import torch +import sys import torch.nn.functional as F from torch import nn from torch.autograd import Variable @@ -9,6 +10,8 @@ from sklearn.metrics import accuracy_score import numpy as np import pandas as pd +np.set_printoptions(suppress=False) + class LogisticRegressionModel(nn.Module): def __init__(self, input_dim, output_dim): super(LogisticRegressionModel, self).__init__() @@ -35,9 +38,8 @@ tTrain = torch.from_numpy(y_train.values.reshape(2945,1)) fTest= torch.from_numpy(x_test.values) tTest = torch.from_numpy(y_test.values) -batch_size = 95 -n_iters = 1000 -num_epochs = int(n_iters / (len(x_train) / batch_size)) +batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 16 +num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5 learning_rate = 0.001 input_dim = 6 output_dim = 1 @@ -48,7 +50,7 @@ criterion = torch.nn.BCELoss(reduction='mean') optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate) for epoch in range(num_epochs): - print ("Epoch #",epoch) + # print ("Epoch #",epoch) model.train() optimizer.zero_grad() # Forward pass @@ -64,6 +66,4 @@ for epoch in range(num_epochs): y_pred = model(fTest) print("predicted Y value: ", y_pred.data) -print ("The accuracy is", accuracy_score(tTest, np.argmax(y_pred.detach().numpy(), axis=1))) - -torch.save(model, 'stroke.pkl') \ No newline at end of file +torch.save(model.state_dict(), 'stroke.pth') \ No newline at end of file diff --git a/stroke.pkl b/stroke.pkl deleted file mode 100644 index 913baeb4ce3211453bf66672c4ae383d8b17816b..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 1855 zcmb7EO>fg!6m^<5ZCz+f2MSYW%GV5}e59GQlyqRq5SZ}cQi3~3780@?`z6n+W9Qn> zWmO3z0%gO3A26f&9iy^AVl^8O5-XOl;s?xP7W1y3X`G-SxYCpL-aYsD_?_!pQPTaA zG&CfA664Z@WcVhv*U7A9FeBGobIPSr>2^ol>oaw|Vc4#&%gbKf4w!AKr0$a-us!#> zXAwsRY34qpHlQ!7;d_|R;kH|c^rkk#_j=RtjRs-F51`*PJ;xy?D2Sq0vL^$$Fxbz*@0dQ9j6lm<15-IW^10GDBKklPG}R!RMRIh z?>A9;x3&w@0W%oUE&g?Jc2AU@)TS`&c!rgPv`O|xuzlh#8lDw8B!F+D!>O#6;l+;a z62pi6CiA$1IoHj_u$;)q%Mn0^@3=GHZ@_exrZ;JSL~%e++$DCMGB_Ah=pnP6K-PVN z7iqOUli^Sg2)7~de0{wj!{KaJ8|1nIuE(eoI3h~qGXF@nDh_4%LEFhOg+lSn+(L0- zZho;)gdepuKQo&l991$5j@?uwC8cB@LRQHrsfRH0I1+uF!3h;kZbq9^k07VQti~H# zs@g^Xd3uO)3G@i-W6sm@6)Jk*S1QcDK!vR(Dtx<0g;kfL=I0$*BL)lk4+Fm`8EpsG z?1ij-SXNSDRa~B3Z+Nx^mp^sY;6Kc|fj^DBDo`?9;nrT=fNKeBm00?+kbb=dD=OTG zrB~Y0Z^qKqSo&%#{r6b6q`K1DmZ}%73+vzdpR*`uE+{XU`{}Y;FGYVQZ{0 zz4Z5s=aHsYwLjTDt_N3dO=HrDZB6SqzdW~GI`*YP=4AZ(mw(i6_3^jhswgRZY|r$h zL*tm}i0%pBU7fsF982w3=2xAp?)0>qCwUj0JgKguMW_%o2oH2k5tbr^&E_?`xXpHUUm_v_ z5nAY7K`)Ab!izQ+#j~D02zv9Vf53U07_%#y8;J&hTLW82K&mecl>yKa-Yta;NixB}#24WxoLgV46sX1ZH^ z#H^OdA!cv~k&E>Xw`@}H*_w&%F@Zb^Z7p`ax((Zfi+#UL?AQL471^UZ-% zfhixnR4%Qomamo9)~=RIAZu~VGj=^4~|o54{`&z6C6&~V6M}HQ`$5_)^`}!g=}!z zr<*Tm=p}Hb2YJ7-E^|GU49-%?)8tVRu+W1=(|7vqTdf_(YQjhl1nD&)eVU zu`+QcahxB=ftpn-3z3Zpt