2% more accuracy ill take it

.gitignore

@@ -185,6 +185,4 @@ ipython_config.py
 
 
 .conda*/
-
+dead/
-data/
-# for rn

.vscode/extensions.json

@@ -1,3 +1,6 @@
 {
-  "recommendations": ["ms-python.python", "ms-toolsai.jupyter"]
+    "recommendations": [
+        "ms-python.python",
+        "ms-toolsai.jupyter"
+    ]
 }

README.md

@@ -14,8 +14,10 @@ how to git? do not `push --force`. prefer pull requests. its like github
 
 we will plan to do this in multiple different ways using scikit-learn and pytorch. tensorflow is ancient.
 
-> [!IMPORTANT]
+> [!NOTE]
-> phase out tensorflow. dont use it.
+> ~phase out tensorflow. dont use it.~
+>
+> its 2 different platforms for 2 different types of people. use whatever ig
 
 maybe also fit more weather related stats? this dataset is taken from nasa so sources are there
 

dataset_update.py

@@ -1,10 +1,11 @@
 import urllib.parse
 import urllib.request
 from datetime import datetime
+from global_config import DATA_FILE_NAME
 
 # Define parameters
 latitude, longitude = 21.04815477090267, 105.80123159165096  # lmao
-start_date = "2010-01-01"
+start_date = "1981-01-01"
 end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 
 # Define desired parameters
@@ -16,9 +17,24 @@ end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 # WS10M           MERRA-2 Wind Speed at 10 Meters (m/s)
 # WD10M           MERRA-2 Wind Direction at 10 Meters (Degrees)
 # more at https://power.larc.nasa.gov/data-access-viewer/
+weather_params = [
+    # "T2M",
+    # "T2M_MAX",
+    # "T2M_MIN",
+    # "T2MDEW",
+    # "PRECTOTCORR",
+    "QV2M",
+    # "RH2M",
+    # "PS",
+    # "CLOUD_AMT",
+    # "WS10M",
+    # "WD10M",
+    # "ALLSKY_KT",
+    # "ALLSKY_SFC_SW_DWN",
+]
 
 params = {
-    "parameters": "QV2M,T2M,PRECTOTCORR",
+    "parameters": ",".join(weather_params),
     "community": "RE",
     "longitude": longitude,
     "latitude": latitude,
@@ -40,7 +56,7 @@ try:
     with urllib.request.urlopen(url) as response:
         if response.status == 200:
             csv_data = response.read().decode("utf-8")
-            with open("hanoi_weather_data.csv", "w", encoding="utf-8") as file:
+            with open(DATA_FILE_NAME, "w", encoding="utf-8") as file:
                 file.write(csv_data)
             print("Data successfully downloaded and saved to 'hanoi_weather_data.csv'.")
         else:

dead/pytorch_port.py

@@ -8,7 +8,7 @@ from sklearn.preprocessing import MinMaxScaler
 import numpy as np
 from load_data import load_this_data
 
-a = load_this_data("dataset.csv")
+a = load_this_data()
 
 # time series forecasting
 
@@ -19,6 +19,7 @@ scaled_data = scaler.fit_transform(a)
 
 
 def create_sequences(data, seq_length):
+    "see this? return[0] is the big x and return[1] is the big y. and h(x) = y. and h(x) is the model."
     xs = []
     ys = []
     for i in range(len(data) - seq_length):

global_config.py

@@ -0,0 +1 @@
+DATA_FILE_NAME = "data/hanoi_weather_data.csv"

load_data.py

@@ -5,9 +5,6 @@ import io
 # from itertools import islice
 from typing import Union
 
-import pandas as pd
-
-
 def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
     headers = []
     exist_startheader = False
@@ -29,59 +26,3 @@ def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
         stream.seek(0)
         return "", stream
     return "\n".join(headers), stream
-
-
-# if __name__ == "__main__":
-#     with open("hanoi_qv2m_latest.csv", "r", encoding="utf-8") as file:
-#         header, file = cut_headers(file)
-#         print("Extracted Header:")
-#         print(header)
-#         data = pd.read_csv(file)
-#         print("\nFirst 5 Lines of Data:")
-#         print(data.head())
-#         print(data.isnull().sum())
-
-
-def load_data(
-    weather_file_name, columns=["Year", "Month", "Day", "Humidity"].copy(), na=-999
-):
-    with open(weather_file_name, "r", encoding="utf-8") as file:
-        _header, file = cut_headers(file)
-        data = pd.read_csv(file, na_values=na)
-    # print(header)
-    data.columns = columns
-    return data
-
-
-def date_combine(data: pd.DataFrame):
-    data["Date"] = pd.to_datetime(data[["Year", "Month", "Day"]])
-    data = data.drop(columns=["Year", "Month", "Day"])
-    data = data.set_index("Date")
-    return data
-
-
-def validate_view(data: pd.DataFrame, verbose=False):
-    if verbose:
-        print(f"Shape with N/A values: {data.shape}")
-        isn = data.isnull().sum().iloc[0]
-        print(f"Count of N/A values: {isn}")
-    data = data.dropna()  # Drop the rows with missing values
-    if verbose:
-        isn = data.isnull().sum().iloc[0]
-        print(f"Count after drop: {isn}")
-        print(data.describe())
-    return data
-
-
-# if __name__ == "__main__":
-def load_this_data(filename, verbose=False):
-    d = load_data(filename)
-    # if verbose:
-    #     print(d.columns)
-    d = date_combine(d)
-    # if verbose:
-    #     print(d.columns)
-    d = validate_view(d, verbose)
-    # if verbose:
-    #     print(d.columns)
-    return d

sklearn_port.py

@@ -0,0 +1,85 @@
+import sys
+import numpy as np
+import pandas as pd
+from sklearn.metrics import r2_score
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error
+import matplotlib.pyplot as plt
+from global_config import DATA_FILE_NAME
+from load_data import cut_headers
+
+# 1. Load data
+
+with open(DATA_FILE_NAME, "r", encoding="utf-8") as file:
+    data_header, csv_file = cut_headers(file)
+    data = pd.read_csv(csv_file, na_values=-999)
+
+if all(z in data.columns for z in ("YEAR", "MO", "DY")):
+    data["date"] = pd.to_datetime(
+        {k: data[v] for v, k in (zip(["YEAR", "MO", "DY"], ["year", "month", "day"]))}
+    )
+    data.drop(inplace=True, columns=["YEAR", "MO", "DY"])
+    data.set_index(["date"], inplace=True)
+data.dropna(inplace=True)
+
+# 2. Normalize data
+scaler = MinMaxScaler()
+print(data.columns)
+scaled_data = scaler.fit_transform(data)
+
+
+# 3. Create sequences for supervised learning
+def create_sequences(data, seq_length):
+    xs, ys = [], []
+    for i in range(len(data) - seq_length):
+        x = data[i : i + seq_length].flatten()
+        y = data[i + seq_length]
+        xs.append(x)
+        ys.append(y)
+    return np.array(xs), np.array(ys)
+
+
+seq_length = 50
+X, y = create_sequences(scaled_data, seq_length)
+
+# 4. Split into training and testing
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.02, shuffle=False)
+
+# 5. Train linear regression model
+model = RandomForestRegressor(
+        n_estimators=200,       # Number of trees
+        # max_features='sqrt',    # Features considered at each split
+        # max_depth=30,           # Maximum depth of each tree
+        # n_jobs=-1,              # Use all CPU cores
+        random_state=42         # Reproducibility
+)
+model.fit(X_train, y_train)
+
+# 6. Make predictions
+predictions = model.predict(X_test)
+
+# 7. Evaluate performance
+mse = mean_squared_error(y_test, predictions)
+r2 = r2_score(y_test, predictions)
+
+print(f"Test MSE: {mse:.4f}")
+print(f"Test r2: {r2:.4f}")
+
+print(f"Score: {model.score(X_test, y_test)}")
+# 8. Inverse transform predictions
+predictions_rescaled = scaler.inverse_transform(predictions.reshape(-1, data.shape[1]))
+y_test_rescaled = scaler.inverse_transform(y_test.reshape(-1, data.shape[1]))
+
+# 9. Plot results
+for i, column in enumerate(data.columns):
+    plt.figure(figsize=(10, 5))
+    plt.plot(y_test_rescaled[:, i], label=f"Actual {column}")
+    plt.plot(predictions_rescaled[:, i], label=f"Predicted {column}")
+    plt.title(f"Actual vs. Predicted for {column}")
+    plt.xlabel("Sample")
+    plt.ylabel("Value")
+    plt.legend()
+    plt.tight_layout()
+    plt.show()

tutorial/pt_tuto.py

@@ -1,304 +0,0 @@
-"""
-This script demonstrates how to port a TensorFlow LSTM model to PyTorch.
-It includes detailed explanations for every step.
-"""
-
-# Step 1: Import necessary libraries
-# ----------------------------------
-# PyTorch is the core library for building and training neural networks.
-# Torch.nn contains modules for defining layers and loss functions.
-# Torch.optim provides optimizers like Adam for training.
-import matplotlib.pyplot as plt
-import numpy as np
-import torch
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import MinMaxScaler
-from torch import nn, optim
-from torch.utils.data import DataLoader, TensorDataset
-
-import sys
-
-sys.path.append(r"c:\Users\Admin\Documents\lecture ass shit\ml1\codemidterm\ml_midterm")
-
-from load_data import load_this_data
-
-# Step 2: Data Preparation
-# ------------------------
-# In PyTorch, data must be converted into tensors. We'll simulate the data
-# preprocessing steps from your TensorFlow code.
-
-
-# Simulate some data (replace this with your actual data loading logic)
-np.random.seed(42)  # For reproducibility
-# data = np.sin(np.linspace(0, 100, 1000))  # Example: Sine wave data
-# data = data.reshape(-1, 1)  # Reshape to (samples, features)
-
-
-# Load the dataset (replace "dataset.csv" with your actual file path)
-data = load_this_data("dataset.csv")
-
-
-# Extract the "Humidity" column as the target variable
-data = data["Humidity"].values.reshape(-1, 1)
-
-# Normalize the data using MinMaxScaler (same as in TensorFlow)
-scaler = MinMaxScaler()
-data_scaled = scaler.fit_transform(data)
-
-# Define lookback window (sequence length for LSTM)
-n_lookback = 100  # Number of past timesteps to consider
-n_features = 1  # Number of features (e.g., 1 for univariate time series)
-
-
-# Helper function to create sequences
-def create_sequences(data, n_lookback):
-    """
-    Create sequences of length n_lookback for LSTM input.
-
-    Args:
-        data: Scaled data as a NumPy array or PyTorch tensor.
-        n_lookback: Number of past timesteps to consider.
-
-    Returns:
-        x: Input sequences of shape (num_samples, n_lookback, n_features).
-        y: Target values of shape (num_samples, 1).
-    """
-    x, y = [], []
-    for i in range(len(data) - n_lookback):
-        x.append(data[i : i + n_lookback])
-        y.append(data[i + n_lookback])
-    return np.array(x), np.array(y)
-
-
-# Split into training and testing sets
-split_index = int(0.8 * len(data_scaled))
-train_data = data_scaled[:split_index]
-test_data = data_scaled[split_index:]
-
-# Create sequences for training and testing
-train_x, train_y = create_sequences(train_data, n_lookback)
-test_x, test_y = create_sequences(test_data, n_lookback)
-
-# train_y = scaler.transform(train_y)
-# test_y = scaler.transform(test_y)
-# Convert sequences to PyTorch tensors
-train_x = torch.tensor(train_x, dtype=torch.float32)
-train_y = torch.tensor(train_y, dtype=torch.float32)
-test_x = torch.tensor(test_x, dtype=torch.float32)
-test_y = torch.tensor(test_y, dtype=torch.float32)
-
-
-# Create datasets and dataloaders
-train_dataset = TensorDataset(train_x, train_y)
-test_dataset = TensorDataset(test_x, test_y)
-
-train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
-test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False)
-
-# Step 3: Define the LSTM Model
-# -----------------------------
-# PyTorch models are defined by subclassing `nn.Module`.
-# The forward method specifies how data flows through the model.
-
-
-# class LSTMModel(nn.Module):
-#     def __init__(self, n_features, n_lookback, n_neurons):
-#         """
-#         Initialize the LSTM model.
-
-#         Args:
-#             n_features: Number of input features (e.g., 1 for univariate time series).
-#             n_lookback: Number of past timesteps to consider.
-#             n_neurons: Number of neurons in each LSTM layer.
-#         """
-#         super(LSTMModel, self).__init__()
-#         self.lstm1 = nn.LSTM(
-#             n_features,
-#             n_neurons,
-#             batch_first=True,
-#             dropout=0.2,
-#         )
-#         self.lstm2 = nn.LSTM(
-#             n_neurons,
-#             n_neurons,
-#             batch_first=True,
-#         )
-#         self.lstm3 = nn.LSTM(n_neurons, n_neurons, batch_first=True)
-#         self.lstm4 = nn.LSTM(n_neurons, n_neurons, batch_first=True)
-#         self.fc = nn.Linear(n_neurons, 1)
-#         self.dropout = nn.Dropout(0.2)
-
-#     def forward(self, x):
-#         """
-#         Forward pass through the model.
-
-#         Args:
-#             x: Input tensor of shape (batch, seq_len, n_features).
-
-#         Returns:
-#             Output tensor of shape (batch, 1).
-#         """
-#         x, _ = self.lstm1(x)
-#         x, _ = self.lstm2(x)
-#         x, _ = self.lstm3(x)
-#         x, _ = self.lstm4(x)
-#         x = self.dropout(x)
-#         x = self.fc(x[:, -1, :])  # Use the last timestep's output
-#         return x
-
-print("Input sequences (x):", train_x.shape)
-print("Target values (y):", train_y.shape)
-
-print("Sample input:", train_x[0])
-print("Corresponding target:", train_y[0])
-
-class LSTMModel(nn.Module):
-    def __init__(self, n_features, n_lookback, n_neurons):
-        super(LSTMModel, self).__init__()
-        self.lstm = nn.LSTM(n_features, n_neurons, batch_first=True, dropout=0.2)
-        self.lstm2 = nn.LSTM(n_neurons, n_neurons, batch_first=True, dropout=0.2)
-
-        self.fc = nn.Linear(n_neurons, 1)
-
-    def forward(self, x):
-        x, _ = self.lstm(x)
-        x, _ = self.lstm2(x)
-        x = self.fc(x[:, -1, :])  # Use the last timestep's output
-        return x
-
-
-# Instantiate the model
-n_neurons = 128  # Number of neurons in the LSTM
-model = LSTMModel(n_features, n_lookback, n_neurons)
-
-# Step 4: Define Loss Function and Optimizer
-# ------------------------------------------
-# Loss function: Mean Squared Error (MSE) for regression tasks.
-# Optimizer: Adam optimizer for efficient training.
-criterion = nn.MSELoss()
-optimizer = optim.Adam(model.parameters(), lr=0.001)
-
-# Step 5: Train the Model
-# -----------------------
-# PyTorch requires an explicit training loop. This gives you full control
-# over the training process.
-
-epochs = 50  # Number of training epochs
-
-# Check for CUDA and set the device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(f"Using device: {device}")
-
-# Move the model to the device
-model = LSTMModel(n_features, n_lookback, n_neurons).to(device)
-
-# scheduler = optim.lr_scheduler.ReduceLROnPlateau(
-    # optimizer, mode="min", patience=5, factor=0.5, min_lr=1e-6
-# )
-# Move data to the device during training and evaluation
-for epoch in range(epochs):
-    model.train()  # Set the model to training mode
-    train_loss = 0.0
-
-    for x_batch, y_batch in train_loader:
-        # Move data to the device
-        x_batch = x_batch.to(device)
-        y_batch = y_batch.to(device)
-        # Reshape input to (batch, seq_len, n_features)
-        x_batch = x_batch.view(-1, n_lookback, n_features)
-        # y_batch = y_batch.view(-1, 1)
-        # print("x_batch shape:", x_batch.shape)
-        # print("y_batch shape:", y_batch.shape)
-        # print("x_batch dtype:", x_batch.dtype)
-        # print("y_batch dtype:", y_batch.dtype)  
-        # break
-        # Zero the gradients from the previous step
-        optimizer.zero_grad()
-
-        # Forward pass: Compute predictions
-        predictions = model(x_batch)
-        # if epoch == 32:
-            # for name, param in model.named_parameters():
-            #     if param.grad is not None:
-            #         print(f"{name} gradient mean: {param.grad.mean().item()}")
-            #     else:
-            #         print(f"{name} has no gradient")
-            # print("Predictions device:", predictions.device)
-            # print("y_batch device:", y_batch.device)
-            # print("Predictions shape:", predictions.shape)
-            # print("y_batch shape:", y_batch.shape)
-        # Compute the loss
-        loss = criterion(predictions, y_batch)
-
-        # Backward pass: Compute gradients
-        loss.backward()
-
-        # Clip gradients to prevent exploding gradients
-        torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
-
-        # Update model parameters
-        optimizer.step()
-        # scheduler.step(train_loss / len(train_loader))
-        # Accumulate the loss for reporting
-        train_loss += loss.item()
-
-    # Print epoch loss
-    print(f"Epoch {epoch+1}/{epochs}, Loss: {train_loss/len(train_loader):.4f}")
-
-    if epoch % 10 == 0:  # Print every 10 epochs
-        print(
-            f"Sample prediction: {predictions[0].item()}, Actual: {y_batch[0].item()}"
-        )
-# Step 6: Evaluate the Model
-# --------------------------
-# Switch to evaluation mode and disable gradient computation.
-model.eval()
-with torch.no_grad():
-    predictions = []
-    actuals = []
-
-    for x_batch, y_batch in test_loader:
-        # Move data to the device
-        x_batch = x_batch.to(device)
-        y_batch = y_batch.to(device)
-
-        # Reshape input to (batch, seq_len, n_features)
-        # x_batch = x_batch.view(-1, n_lookback, n_features)
-
-        # Make predictions
-        preds = model(x_batch)
-
-        # Move predictions and actuals back to CPU for further processing
-        predictions.append(preds.cpu().numpy())
-        actuals.append(y_batch.cpu().numpy())
-
-# Convert predictions and actuals to NumPy arrays for comparison
-predictions = np.concatenate(predictions)
-actuals = np.concatenate(actuals)
-
-# Step 7: Post-Processing and Visualization
-# -----------------------------------------
-# Inverse transform the predictions and actuals to get original scale
-predictions = scaler.inverse_transform(predictions)
-actuals = scaler.inverse_transform(actuals)
-
-# Plot the results
-print("Sample scaled train_y:", train_y[:5])
-print("Sample scaled test_y:", test_y[:5])
-
-print("Predictions shape:", predictions.shape)
-print("Actuals shape:", actuals.shape)
-
-print("Sample inverse-transformed predictions:", predictions[:5])
-print("Sample inverse-transformed actuals:", actuals[:5])
-
-plt.figure(figsize=(20, 5))
-plt.plot(actuals, label="Actual")
-plt.plot(predictions, label="Predicted")
-plt.legend()
-plt.show()
-
-from sklearn.metrics import r2_score, mean_squared_error
-
-print("R² Score:", r2_score(actuals, predictions))
-print("MSE:", mean_squared_error(actuals, predictions))

tutorial/pytorch_test.py

@@ -1,124 +0,0 @@
-"""this uses new tech
-make by conda new -p path python=3.12; conda activate -p path; conda install all those shi
-
-conda install pytorch torchvision torchaudio pytorch-cuda -c pytorch -c nvidia
-"""
-
-import sys
-
-sys.path.append(".")
-from load_data import load_this_data
-import torch
-
-# a = load_this_data("dataset.csv")
-
-x = torch.tensor([[1, 2], [3, 4]])
-print(x)
-
-
-print(x.shape)       # Output: torch.Size([2, 2])
-print(x.dtype)       # Output: torch.int64
-print(x.device)      # Output: cpu
-
-y = torch.ones_like(x)
-print(x + y)
-print(x * y)
-
-
-x = torch.randn(3, requires_grad=True)
-y = x * 2
-z = y.mean()
-z.backward()
-print(x.grad)
-
-import torch.nn as nn
-
-class SimpleNet(nn.Module):
-    def __init__(self):
-        super(SimpleNet, self).__init__()
-        self.fc = nn.Linear(2, 1)
-
-    def forward(self, x):
-        return self.fc(x)
-
-
-model = SimpleNet()
-sample_input = torch.tensor([[1.0, 2.0]])
-output = model(sample_input)
-print(output)
-
-import torch.optim as optim
-
-criterion = nn.MSELoss()
-optimizer = optim.SGD(model.parameters(), lr=0.01)
-
-for epoch in range(100):
-    optimizer.zero_grad()
-    outputs = model(sample_input)
-    loss = criterion(outputs, torch.tensor([[1.0]]))
-    loss.backward()
-    optimizer.step()
-    if (epoch+1) % 10 == 0:
-        print(f'Epoch [{epoch+1}/100], Loss: {loss.item():.4f}')
-
-model.eval()
-
-sample_input_2 = torch.tensor([[1.0, 2.0], [3.0, 4.0]])
-output_2 = model(sample_input_2)
-print(output_2)
-
-
-from torchvision import datasets, transforms
-from torch.utils.data import DataLoader
-
-# Define a transform to normalize the data
-transform = transforms.Compose([transforms.ToTensor()])
-
-# Download and load the training data
-train_dataset = datasets.MNIST(root='data', train=True, download=True, transform=transform)
-train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
-
-
-# import torch.nn as nn
-import torch.nn.functional as F
-
-class Net(nn.Module):
-    def __init__(self):
-        super(Net, self).__init__()
-        self.fc1 = nn.Linear(28 * 28, 128)
-        self.fc2 = nn.Linear(128, 10)
-
-    def forward(self, x):
-        x = x.view(-1, 28 * 28)  # Flatten the input
-        x = F.relu(self.fc1(x))
-        x = self.fc2(x)
-        return x
-
-model_2 = Net()
-criterion_2 = nn.CrossEntropyLoss()
-optimizer_2 = torch.optim.SGD(model.parameters(), lr=0.01)
-
-
-for epoch in range(35):  # loop over the dataset multiple times
-    for inputs, labels in train_loader:
-        optimizer_2.zero_grad()           # zero the parameter gradients
-        outputs = model_2(inputs)         # forward
-        loss = criterion_2(outputs, labels)  # compute loss
-        loss.backward()                 # backward
-        optimizer_2.step()                # optimize
-    print(f'Epoch {epoch+1}, Loss: {loss.item()}')
-
-
-test_dataset = datasets.MNIST(root='data', train=False, download=True, transform=transform)
-test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)
-
-
-correct = 0
-total = 0
-with torch.no_grad():
-    for inputs, labels in test_loader:
-        outputs = model_2(inputs)
-        _, predicted = torch.max(outputs.data, 1)
-        total += labels.size(0)
-        correct += (predicted == labels).sum().item()
-print(f'Accuracy: {100 * correct / total}%')