From d95bf0d73d616d25b5cad52d214b644e8c659ec5 Mon Sep 17 00:00:00 2001
From: Marcin Kostrzewski <komar86311@gmail.com>
Date: Sun, 24 Apr 2022 22:20:14 +0200
Subject: [PATCH] Added regression model training

---
 requirements.txt |   4 +-
 train_model.py   | 111 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 114 insertions(+), 1 deletion(-)
 create mode 100644 train_model.py

diff --git a/requirements.txt b/requirements.txt
index 3a40842..08cc030 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,4 @@
 kaggle==1.5.12
-pandas==1.4.1
\ No newline at end of file
+pandas==1.4.1
+torch==1.11.0
+numpy~=1.22.3
\ No newline at end of file
diff --git a/train_model.py b/train_model.py
new file mode 100644
index 0000000..bdf091a
--- /dev/null
+++ b/train_model.py
@@ -0,0 +1,111 @@
+import numpy as np
+import pandas as pd
+import torch
+from torch import nn
+from torch.utils.data import DataLoader, Dataset
+
+
+def hour_to_int(text: str):
+    return float(text.replace(':', ''))
+
+
+def int_to_hour(num: int):
+    return str(num)
+
+
+class PlantsDataset(Dataset):
+    def __init__(self, file_name):
+        df = pd.read_csv(file_name)
+
+        x = np.array([x[0].split(' ')[1] for x in df.iloc[:, 0:1].values])
+        y = df.iloc[:, 3].values
+
+        x_processed = np.array([hour_to_int(h) for h in x], dtype='float32')
+
+        self.x_train = torch.from_numpy(x_processed)
+        self.y_train = torch.from_numpy(y)
+        self.x_train.type(torch.LongTensor)
+
+    def __len__(self):
+        return len(self.y_train)
+
+    def __getitem__(self, idx):
+        return self.x_train[idx].float(), self.y_train[idx].float()
+
+
+class MLP(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.layers = nn.Sequential(
+            nn.Linear(1, 64),
+            nn.ReLU(),
+            nn.Linear(64, 32),
+            nn.ReLU(),
+            nn.Linear(32, 1),
+        )
+
+    def forward(self, x):
+        x = x.view(x.size(0), -1)
+        return self.layers(x)
+
+
+def train(dataloader, model, loss_fn, optimizer):
+    size = len(dataloader.dataset)
+    model.train()
+    for batch, (X, y) in enumerate(dataloader):
+        X, y = X.to(device), y.to(device)
+
+        # Compute prediction error
+        pred = model(X)
+        loss = loss_fn(pred, y)
+
+        # Backpropagation
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        if batch % 100 == 0:
+            loss, current = loss.item(), batch * len(X)
+            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")
+
+
+def test(dataloader, model, loss_fn):
+    num_batches = len(dataloader)
+    model.eval()
+    test_loss, correct = 0, 0
+    with torch.no_grad():
+        for X, y in dataloader:
+            X, y = X.to(device), y.to(device)
+            pred = model(X)
+            test_loss += loss_fn(pred, y).item()
+    test_loss /= num_batches
+    print(f"Avg loss: {test_loss:>8f} \n")
+
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+print(f"Using {device} device")
+
+batch_size = 64
+
+plant_test = PlantsDataset('data/Plant_1_Generation_Data.csv.test')
+plant_train = PlantsDataset('data/Plant_1_Generation_Data.csv.train')
+
+train_dataloader = DataLoader(plant_train, batch_size=batch_size)
+test_dataloader = DataLoader(plant_test, batch_size=batch_size)
+
+for i, (data, labels) in enumerate(train_dataloader):
+    print(data.shape, labels.shape)
+    print(data, labels)
+    break
+
+model = MLP()
+print(model)
+
+loss_fn = nn.MSELoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
+epochs = 5
+for t in range(epochs):
+    print(f"Epoch {t + 1}\n-------------------------------")
+    train(train_dataloader, model, loss_fn, optimizer)
+    test(test_dataloader, model, loss_fn)
+print("Done!")