From ee20c963609575f365d27edfc7cd004b0b36b939 Mon Sep 17 00:00:00 2001 From: s434766 Date: Thu, 13 May 2021 23:06:29 +0200 Subject: [PATCH] sacred --- Dockerfile | 2 +- pytorch-training-eval/Dockerfile | 3 +- sacred-pytorch1.py | 85 +++++++++++++++++++++++++++++++ sacred-pytorch2.py | 86 ++++++++++++++++++++++++++++++++ stroke-pytorch.py | 14 ++---- 5 files changed, 177 insertions(+), 13 deletions(-) create mode 100644 sacred-pytorch1.py create mode 100644 sacred-pytorch2.py diff --git a/Dockerfile b/Dockerfile index 89570a4..b3839ea 100644 --- a/Dockerfile +++ b/Dockerfile @@ -2,7 +2,7 @@ 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 && pip3 install matplotlib && rm -rf /var/lib/apt/lists/* RUN pip3 install torch torchvision torchaudio -RUN pip3 install sacred +RUN pip3 install sacred && pip3 install GitPython WORKDIR /app COPY ./create.py ./ diff --git a/pytorch-training-eval/Dockerfile b/pytorch-training-eval/Dockerfile index c13fe04..c1fe5f0 100644 --- a/pytorch-training-eval/Dockerfile +++ b/pytorch-training-eval/Dockerfile @@ -1,7 +1,8 @@ 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 && pip3 install matplotlib && 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 +RUN pip3 install sacred && pip3 install GitPython WORKDIR /app COPY ./../create.py ./ diff --git a/sacred-pytorch1.py b/sacred-pytorch1.py new file mode 100644 index 0000000..ecadab6 --- /dev/null +++ b/sacred-pytorch1.py @@ -0,0 +1,85 @@ +import torch +import sys +import torch.nn.functional as F +from torch import nn +from sklearn.metrics import accuracy_score, mean_squared_error +import numpy as np +import pandas as pd +from sacred import Experiment +from sacred.observers import FileStorageObserver + +np.set_printoptions(suppress=False) + +ex = Experiment("ium_s434766", interactive=False, save_git_info=False) +ex.observers.append(FileStorageObserver("ium_s434766/my_runs")) + +@ex.config +def my_config(): + num_epochs = 15 + batch_size = 16 + learning_rate = 0.001 + +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) + +@ex.capture +def train(num_epochs, batch_size, learning_rate, _run): + data_train = pd.read_csv("data_train.csv") + data_test = pd.read_csv("data_test.csv") + FEATURES = ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi'] + + x_train = data_train[FEATURES].astype(np.float32) + y_train = data_train['stroke'].astype(np.float32) + + x_test = data_test[FEATURES].astype(np.float32) + y_test = data_test['stroke'].astype(np.float32) + + fTrain = torch.from_numpy(x_train.values) + tTrain = torch.from_numpy(y_train.values.reshape(2945,1)) + + fTest= torch.from_numpy(x_test.values) + tTest = torch.from_numpy(y_test.values) + + + input_dim = 6 + output_dim = 1 + info_params = "Batch size = " + str(batch_size) + " Epochs = " + str(num_epochs) + _run.info(info_params) + model = LogisticRegressionModel(input_dim, output_dim) + + criterion = torch.nn.BCELoss(reduction='mean') + optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate) + + for epoch in range(num_epochs): + # print ("Epoch #",epoch) + model.train() + optimizer.zero_grad() + # Forward pass + y_pred = model(fTrain) + # Compute Loss + loss = criterion(y_pred, tTrain) + # print(loss.item()) + # Backward pass + loss.backward() + optimizer.step() + + info_loss = "Last loss = " + str(loss.item()) + _run.info(info_loss) + y_pred = model(fTest) + print("predicted Y value: ", y_pred.data) + + torch.save(model.state_dict(), 'stroke.pth') + + +@ex.automain +def my_main(num_epochs, batch_size, learning_rate, _run): + train() + +r = ex.run() +ex.add_artifact("stroke_model/stroke.pth") \ No newline at end of file diff --git a/sacred-pytorch2.py b/sacred-pytorch2.py new file mode 100644 index 0000000..71354e8 --- /dev/null +++ b/sacred-pytorch2.py @@ -0,0 +1,86 @@ +import torch +import sys +import torch.nn.functional as F +from torch import nn +from sklearn.metrics import accuracy_score, mean_squared_error +import numpy as np +import pandas as pd +from sacred import Experiment +from sacred.observers import MongoObserver + +np.set_printoptions(suppress=False) + +ex = Experiment("ium_s434766", interactive=False, save_git_info=False) +ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017', + db_name='sacred')) + +@ex.config +def my_config(): + num_epochs = 15 + batch_size = 16 + learning_rate = 0.001 + +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) + +@ex.capture +def train(num_epochs, batch_size, learning_rate, _run): + data_train = pd.read_csv("data_train.csv") + data_test = pd.read_csv("data_test.csv") + FEATURES = ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi'] + + x_train = data_train[FEATURES].astype(np.float32) + y_train = data_train['stroke'].astype(np.float32) + + x_test = data_test[FEATURES].astype(np.float32) + y_test = data_test['stroke'].astype(np.float32) + + fTrain = torch.from_numpy(x_train.values) + tTrain = torch.from_numpy(y_train.values.reshape(2945,1)) + + fTest= torch.from_numpy(x_test.values) + tTest = torch.from_numpy(y_test.values) + + + input_dim = 6 + output_dim = 1 + info_params = "Batch size = " + str(batch_size) + " Epochs = " + str(num_epochs) + _run.info(info_params) + model = LogisticRegressionModel(input_dim, output_dim) + + criterion = torch.nn.BCELoss(reduction='mean') + optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate) + + for epoch in range(num_epochs): + # print ("Epoch #",epoch) + model.train() + optimizer.zero_grad() + # Forward pass + y_pred = model(fTrain) + # Compute Loss + loss = criterion(y_pred, tTrain) + # print(loss.item()) + # Backward pass + loss.backward() + optimizer.step() + + info_loss = "Last loss = " + str(loss.item()) + _run.info(info_loss) + y_pred = model(fTest) + print("predicted Y value: ", y_pred.data) + + torch.save(model.state_dict(), 'stroke.pth') + + +@ex.automain +def my_main(num_epochs, batch_size, learning_rate, _run): + train() + +r = ex.run() +ex.add_artifact("stroke_model/stroke.pth") \ No newline at end of file diff --git a/stroke-pytorch.py b/stroke-pytorch.py index c54f9aa..255ef6b 100644 --- a/stroke-pytorch.py +++ b/stroke-pytorch.py @@ -13,10 +13,7 @@ from sacred import Experiment from sacred.observers import FileStorageObserver np.set_printoptions(suppress=False) -# ex = Experiment("stroke-pytorch", interactive=True) -# ex.observers.append(FileStorageObserver('ium_s434766O_files')) -# ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@localhost:27017', -# db_name='sacred')) + class LogisticRegressionModel(nn.Module): def __init__(self, input_dim, output_dim): super(LogisticRegressionModel, self).__init__() @@ -26,8 +23,7 @@ class LogisticRegressionModel(nn.Module): out = self.linear(x) return self.sigmoid(out) -# @ex.main -# def my_main(_log): + data_train = pd.read_csv("data_train.csv") data_test = pd.read_csv("data_test.csv") data_val = pd.read_csv("data_val.csv") @@ -50,8 +46,7 @@ num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5 learning_rate = 0.001 input_dim = 6 output_dim = 1 -info_params = "Batch size = " + str(batch_size) + " Epochs = " + str(num_epochs) -# _log.info(info_params) + model = LogisticRegressionModel(input_dim, output_dim) criterion = torch.nn.BCELoss(reduction='mean') @@ -69,11 +64,8 @@ for epoch in range(num_epochs): # Backward pass loss.backward() optimizer.step() -info_loss = "Last loss = " + str(loss.item()) - # _log.info(info_loss) y_pred = model(fTest) print("predicted Y value: ", y_pred.data) torch.save(model.state_dict(), 'stroke.pth') -# ex.run() \ No newline at end of file