48 lines
1.2 KiB
Python
48 lines
1.2 KiB
Python
import pandas as pd
|
|
import torch
|
|
import torch.nn as nn
|
|
from sklearn.preprocessing import StandardScaler
|
|
|
|
df = pd.read_csv("./RegressionModels/CaliforniaHousing/housing.csv")
|
|
|
|
|
|
df = df.dropna(subset=df.columns[:8])
|
|
df['ocean_proximity_encoded'] = df['ocean_proximity'].astype('category').cat.codes #Encodes text values as numerical ones
|
|
|
|
# print(df)
|
|
# print(df.iloc[:,0:8])
|
|
|
|
scaler_x = StandardScaler()
|
|
scaled_X = scaler_x.fit_transform(df.iloc[:,0:8].join(df["ocean_proximity_encoded"]).values)
|
|
X = torch.tensor(scaled_X, dtype=torch.float32)
|
|
|
|
scaler_y = StandardScaler()
|
|
scaled_Y = scaler_y.fit_transform(df["median_house_value"].values.reshape(-1,1))
|
|
Y = torch.tensor(scaled_Y, dtype=torch.float32)
|
|
|
|
model = torch.nn.Sequential(
|
|
torch.nn.Linear(9, 18),
|
|
torch.nn.ReLU(),
|
|
torch.nn.Linear(18, 1)
|
|
)
|
|
|
|
loss_fn = torch.nn.MSELoss()
|
|
optimizer = torch.optim.SGD(model.parameters(), lr=1e-2)
|
|
|
|
|
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
|
model = model.to(device)
|
|
X = X.to(device)
|
|
Y = Y.to(device)
|
|
|
|
|
|
for epoch in range(3000):
|
|
pred_y = model(X)
|
|
loss = loss_fn(pred_y, Y)
|
|
optimizer.zero_grad()
|
|
loss.backward()
|
|
optimizer.step()
|
|
if epoch % 99 == 0:
|
|
print('Epoch: ', epoch, f"loss: {loss.item():.2f}")
|
|
|