2% more accuracy ill take it

.gitignore

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

data_loader.py

@@ -1,43 +0,0 @@
-import pandas as pd
-import io
-from typing import Union
-
-
-def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
-    """Remove custom header metadata from the CSV file."""
-    headers = []
-    exist_startheader = False
-    while line := stream.readline():
-        if "-BEGIN HEADER-" in line and not exist_startheader:
-            exist_startheader = True
-            headers.append(str(line.strip()))
-        elif "-END HEADER-" in line and exist_startheader:
-            headers.append(str(line.strip()))
-            break
-        elif exist_startheader:
-            headers.append(str(line.strip()))
-        elif not exist_startheader:
-            continue
-    if not exist_startheader:
-        stream.seek(0)
-        return "", stream
-    return "\n".join(headers), stream
-
-
-def load_weather_data(file_path: str) -> pd.DataFrame:
-    """Load weather data and preprocess the datetime index."""
-    with open(file_path, "r", encoding="utf-8") as file:
-        _, csv_file = cut_headers(file)
-        data = pd.read_csv(csv_file, na_values=-999)
-
-    # Convert YEAR, MO, DY to datetime index
-    if all(col in data.columns for col 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(columns=["YEAR", "MO", "DY"], inplace=True)
-        data.set_index("date", inplace=True)
-
-    data.dropna(inplace=True)
-    data = data.asfreq("D")  # Assumes regular daily data
-    return data

dataset_update.py

@@ -1,12 +1,11 @@
 import urllib.parse
 import urllib.request
 from datetime import datetime
-
+from global_config import DATA_FILE_NAME
-data_file = "hanoi_weather_data.csv"
 
 # Define parameters
 latitude, longitude = 21.04815477090267, 105.80123159165096  # lmao
-start_date = "1985-01-01"
+start_date = "1981-01-01"
 end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 
 # Define desired parameters
@@ -19,7 +18,19 @@ end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 # 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 = {
@@ -41,15 +52,14 @@ base_url = "https://power.larc.nasa.gov/api/temporal/daily/point"
 url = f"{base_url}?{query_string}"
 
 # Make the API request using urllib
-if __name__ == "__main__":
+try:
-    try:
+    with urllib.request.urlopen(url) as response:
-        with urllib.request.urlopen(url) as response:
+        if response.status == 200:
-            if response.status == 200:
+            csv_data = response.read().decode("utf-8")
-                csv_data = response.read()
+            with open(DATA_FILE_NAME, "w", encoding="utf-8") as file:
-                with open(data_file, "wb") as file:
+                file.write(csv_data)
-                    file.write(csv_data)
+            print("Data successfully downloaded and saved to 'hanoi_weather_data.csv'.")
-                print(f"Data successfully downloaded and saved to {data_file}.")
+        else:
-            else:
+            print(f"Failed to retrieve data: HTTP Status Code {response.status}")
-                print(f"Failed to retrieve data: HTTP Status Code {response.status}")
+except urllib.error.URLError as e:
-    except urllib.error.URLError as e:
+    print(f"Failed to retrieve data: {e.reason}")
-        print(f"Failed to retrieve data: {e.reason}")

dead/dead/pytorch_port.py

@@ -1,163 +0,0 @@
-from sklearn.model_selection import train_test_split
-import torch
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-from sklearn.preprocessing import MinMaxScaler
-
-import numpy as np
-from load_data import load_this_data
-
-a = load_this_data()
-
-# time series forecasting
-
-
-scaler = MinMaxScaler()
-print(a.columns)
-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):
-        x = data[i : (i + seq_length)]
-        y = data[i + seq_length]
-        xs.append(x)
-        ys.append(y)
-    return np.array(xs), np.array(ys)
-
-
-seq_length = 20
-
-X, y = create_sequences(scaled_data, seq_length)
-
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y, test_size=0.2, random_state=42
-)
-from torch.utils.data import TensorDataset, DataLoader
-
-X_train_tensor = torch.tensor(X_train, dtype=torch.float32)
-y_train_tensor = torch.tensor(y_train, dtype=torch.float32)
-
-train_dataset = TensorDataset(X_train_tensor, y_train_tensor)
-train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)
-
-
-import torch.nn as nn
-
-
-class LSTMModel(nn.Module):
-    def __init__(self, input_size, hidden_size, num_layers, output_size):
-        super(LSTMModel, self).__init__()
-        self.hidden_size = hidden_size
-        self.num_layers = num_layers
-        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
-        self.fc = nn.Linear(hidden_size, output_size)
-
-    def forward(self, x):
-        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
-        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
-
-        out, _ = self.lstm(x, (h0, c0))
-        out = self.fc(out[:, -1, :])  # Take the output from the last time step
-        return out
-
-
-model = LSTMModel(
-    input_size=X_train.shape[2],
-    hidden_size=64,
-    num_layers=2,
-    output_size=y_train.shape[1],
-)
-model.to(device)
-criterion = nn.MSELoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
-
-train_losses = []
-val_losses = []
-
-
-for epoch in range(100):
-    model.train()
-    running_train_loss = 0.0
-
-    # inputs, targets
-    for batch_X, batch_y in train_loader:
-        batch_X = batch_X.to(device)
-        batch_y = batch_y.to(device)
-
-        outputs = model(batch_X)
-        loss = criterion(outputs, batch_y)
-
-        optimizer.zero_grad()
-        loss.backward()
-        optimizer.step()
-
-        running_train_loss += loss.item() * batch_X.size(0)
-    if (epoch + 1) % 10 == 0:
-        print(f"Epoch [{epoch+1}/100], Loss: {loss.item():.4f}")
-
-    epoch_train_loss = running_train_loss / len(train_loader.dataset)
-    train_losses.append(epoch_train_loss)
-
-model.eval()
-
-X_test_tensor = torch.tensor(X_test, dtype=torch.float32).to(device)
-y_test_tensor = torch.tensor(y_test, dtype=torch.float32).to(device)
-val_dataset = TensorDataset(X_test_tensor, y_test_tensor)
-val_loader = DataLoader(val_dataset, batch_size=64, shuffle=False)
-
-# with torch.no_grad():
-#     running_val_loss = 0.0
-#     predictions = model(X_test_tensor)
-#     test_loss = criterion(predictions, y_test_tensor)
-#     print(f"Test Loss: {test_loss.item():.4f}")
-
-running_val_loss = 0.0
-predictions = []
-with torch.no_grad():
-    for inputs, targets in val_loader:
-        inputs, targets = inputs.to(device), targets.to(device)
-        outputs = model(inputs)
-        loss = criterion(outputs, targets)
-        running_val_loss += loss.item() * inputs.size(0)
-        predictions.append(outputs.cpu().numpy())  # Collect all batches
-
-epoch_val_loss = running_val_loss / len(val_loader.dataset)  # len(val_dataset)
-val_losses.append(epoch_val_loss)
-
-predictions = np.concatenate(predictions, axis=0)
-import matplotlib.pyplot as plt
-
-y_test_cpu = y_test_tensor.cpu().numpy()
-
-predictions_rescaled = scaler.inverse_transform(predictions)
-y_test_rescaled = scaler.inverse_transform(y_test_cpu)
-
-
-fig, (ax1, ax2) = plt.subplots(
-    1, 2, figsize=(14, 5), gridspec_kw={"width_ratios": [1, 3]}
-)
-
-# Loss curve on the left
-ax1.plot(train_losses, label="Train Loss")
-ax1.plot(val_losses, label="Val Loss")
-ax1.set_title("Loss Curve")
-ax1.set_xlabel("Epoch")
-ax1.set_ylabel("Loss")
-ax1.legend()
-ax1.grid(True)
-
-# Prediction vs Actual on the right
-ax2.plot(y_test_rescaled, label="Actual")
-ax2.plot(predictions_rescaled, label="Predicted")
-ax2.set_title("Actual vs. Predicted")
-ax2.set_xlabel("Sample")
-ax2.set_ylabel("Value")
-ax2.legend()
-
-plt.tight_layout()
-plt.show()

dead/global_config.py

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

dead/sk2_port.py

@@ -1,185 +0,0 @@
-import sys
-import numpy as np
-import pandas as pd
-import matplotlib.pyplot as plt
-import seaborn as sns
-import io
-from typing import Union
-from sklearn.metrics import mean_squared_error, r2_score
-from sklearn.preprocessing import MinMaxScaler
-from sklearn.model_selection import train_test_split
-from sklearn.linear_model import LinearRegression
-from statsmodels.tsa.ar_model import AutoReg
-
-# ==== LOAD & CLEAN DATA ====
-DATA_FILE_NAME = "hanoi_weather_data.csv"
-
-def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
-    headers = []
-    exist_startheader = False
-    while line := stream.readline():
-        if "-BEGIN HEADER-" in line and not exist_startheader:
-            exist_startheader = True
-            headers.append(str(line.strip()))
-        elif "-END HEADER-" in line and exist_startheader:
-            headers.append(str(line.strip()))
-            break
-        elif exist_startheader:
-            headers.append(str(line.strip()))
-        elif not exist_startheader:
-            continue
-    if not exist_startheader:
-        stream.seek(0)
-        return "", stream
-    return "\n".join(headers), stream
-
-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(columns=["YEAR", "MO", "DY"], inplace=True)
-    data.set_index("date", inplace=True)
-
-data.dropna(inplace=True)
-
-# ==== VISUALIZE CORRELATION ====
-plt.figure(figsize=(12, 8))
-sns.heatmap(data.corr(), annot=True, cmap="coolwarm")
-plt.title("Feature Correlation Heatmap")
-plt.show()
-
-# ==== SCALE DATA ====
-scaler = MinMaxScaler()
-scaled_data = scaler.fit_transform(data)
-
-# ==== CREATE SEQUENCES ====
-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)
-
-# ==== SPLIT ====
-date_index = data.index[seq_length:]
-X_train, X_test, y_train, y_test, date_train, date_test = train_test_split(
-    X, y, date_index, test_size=0.02, shuffle=False
-)
-
-# ==== TRAIN LINEAR REGRESSION ====
-model = LinearRegression()
-model.fit(X_train, y_train)
-predictions = model.predict(X_test)
-
-# ==== EVALUATION ====
-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"Model Score: {model.score(X_test, y_test):.4f}")
-
-# ==== INVERSE TRANSFORM ====
-predictions_rescaled = scaler.inverse_transform(
-    predictions.reshape(-1, data.shape[1])
-)
-y_test_rescaled = scaler.inverse_transform(
-    y_test.reshape(-1, data.shape[1])
-)
-
-# ==== PLOTS ====
-
-# Actual vs Predicted with Real Dates
-plt.figure(figsize=(12, 6))
-plt.plot(date_test, y_test_rescaled[:, 0], label="Actual")
-plt.plot(date_test, predictions_rescaled[:, 0], label="Predicted")
-plt.title("Actual vs Predicted (First Feature)")
-plt.xlabel("Date")
-plt.ylabel("Original Scale")
-plt.xticks(rotation=45)
-plt.legend()
-plt.grid(True)
-plt.tight_layout()
-plt.show()
-
-# Residual Plot
-residuals = y_test[:, 0] - predictions[:, 0]
-plt.figure(figsize=(10, 4))
-plt.plot(date_test, residuals, label="Residuals")
-plt.hlines(0, 0, len(residuals), colors="red")
-plt.title("Residuals Over Time (First Feature)")
-plt.xlabel("Date")
-plt.ylabel("Error")
-plt.xticks(rotation=45)
-plt.legend()
-plt.tight_layout()
-plt.grid(True)
-plt.show()
-
-# Error Distribution
-errors = np.abs(y_test[:, 0] - predictions[:, 0])
-plt.hist(errors, bins=50)
-plt.title("Error Distribution (First Feature)")
-plt.xlabel("Absolute Error")
-plt.ylabel("Frequency")
-plt.grid(True)
-plt.show()
-
-# Scatter Plot
-plt.scatter(y_test[:, 0], predictions[:, 0], alpha=0.5)
-plt.plot([0, 1], [0, 1], "r--")
-plt.title("Predicted vs Actual (Normalized)")
-plt.xlabel("Actual")
-plt.ylabel("Predicted")
-plt.grid(True)
-plt.show()
-
-# ==== AUTOREGRESSION FORECAST ====
-target_column = data.columns[0]
-series = data[target_column]
-
-train_size = int(len(series) * 0.98)
-train_series = series[:train_size]
-test_series = series[train_size:]
-
-ar_model = AutoReg(train_series, lags=30).fit()
-ar_preds = ar_model.predict(start=len(train_series), end=len(series)-1)
-
-# Plot AR Forecast
-plt.figure(figsize=(12, 5))
-plt.plot(test_series.index, test_series, label="Actual")
-plt.plot(test_series.index, ar_preds, label="AR Forecast", linestyle="--")
-plt.title(f"AutoRegression Forecast - {target_column}")
-plt.xlabel("Date")
-plt.ylabel(target_column)
-plt.xticks(rotation=45)
-plt.legend()
-plt.grid(True)
-plt.tight_layout()
-plt.show()
-
-# ==== FUTURE FORECAST ====
-future_steps = 30
-future_index = pd.date_range(start=series.index[-1], periods=future_steps+1, freq="D")[1:]
-future_forecast = ar_model.predict(start=len(series), end=len(series) + future_steps - 1)
-
-plt.figure(figsize=(12, 5))
-plt.plot(series[-100:], label="Recent Data")
-plt.plot(future_index, future_forecast, label="Future Forecast", color="red")
-plt.title(f"{target_column} - 30 Day Forecast (AutoRegression)")
-plt.xlabel("Date")
-plt.ylabel(target_column)
-plt.xticks(rotation=45)
-plt.legend()
-plt.tight_layout()
-plt.grid(True)
-plt.show()

global_config.py

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

main.py

@@ -1,71 +0,0 @@
-# import pandas as pd
-from data_loader import load_weather_data
-from preprocessing import scale_data, create_sequences, inverse_scale
-from model_train import (
-    train_linear_regression_gd,
-    predict_linear_regression,
-    evaluate_model,
-)
-from visualize import (
-    plot_original_vs_scaled,
-    plot_predictions,
-    plot_residuals,
-    plot_error_hist,
-    plot_scatter,
-    plot_loss_curve,
-    plot_value_distribution,
-    visualize_sequence_window,
-)
-from sklearn.model_selection import train_test_split
-
-# Step 1: Load data
-data = load_weather_data("hanoi_weather_data.csv")
-
-plot_value_distribution(data)
-
-# Step 2: Preprocess (scale and sequence)
-scaled_data, scaler = scale_data(data)
-plot_original_vs_scaled(data, scaled_data)
-
-seq_length = 50
-X, y = create_sequences(scaled_data, seq_length)
-
-visualize_sequence_window(data["QV2M"], seq_length=10, start_idx=1000)
-
-# Step 3: Train/test split
-date_index = data.index[seq_length:]
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y.reshape(-1), test_size=0.02, shuffle=False
-)
-date_train, date_test = train_test_split(date_index, test_size=0.02, shuffle=False)
-
-# Step 4: Train model with gradient descent
-# import math
-# lr_schedule = lambda epoch: max(0.005, 0.01 * (1 + math.cos(epoch / 1000 * math.pi)) / 2)
-
-theta, losses = train_linear_regression_gd(
-    X_train,
-    y_train,
-    # lr_schedule=lr_schedule,
-    n_epochs=10000,
-)
-
-predictions = predict_linear_regression(X_test, theta)
-
-# Step 5: Evaluate
-mse, r2 = evaluate_model(y_test, predictions)
-print(f"MSE: {mse:.4f}, R2: {r2:.4f}")
-
-# Step 6: Rescale predictions
-y_test_rescaled = inverse_scale(y_test, scaler, data.shape[1])
-predictions_rescaled = inverse_scale(predictions, scaler, data.shape[1])
-
-# Step 7: Visualize
-residuals = y_test - predictions
-errors = abs(residuals)
-
-plot_predictions(date_test, y_test_rescaled, predictions_rescaled)
-plot_residuals(date_test.to_numpy(), residuals)
-plot_error_hist(errors)
-plot_scatter(y_test.reshape(-1, 1), predictions.reshape(-1, 1))
-plot_loss_curve(losses)

model_train.py

@@ -1,45 +0,0 @@
-import numpy as np
-from sklearn.metrics import mean_squared_error, r2_score
-
-
-def train_linear_regression_gd(X_train, y_train, lr_schedule= lambda _e: 0.01, n_epochs=1000):
-    """
-    Train linear regression model using batch gradient descent.
-
-    Returns:
-        theta: learned weights
-        losses: list of MSE loss per epoch
-    """
-    m, n = X_train.shape
-    X_b = np.hstack([np.ones((m, 1)), X_train])
-    theta = np.zeros(n + 1)
-    losses = []
-
-    for epoch in range(n_epochs):
-        lr = lr_schedule(epoch)
-        predictions = X_b @ theta
-        errors = predictions - y_train
-        gradients = (2 / m) * X_b.T @ errors
-        gradients = np.clip(gradients, -1, 1)  # gradient clipping
-        theta -= lr * gradients
-        loss = np.mean(errors ** 2)
-        losses.append(loss)
-
-        if epoch % 1000 == 0:
-            print(f"Epoch {epoch}: Loss = {loss:.6f}, LR: {lr:.6f}")
-
-    print(f"Final Loss: {losses[-1]:.6f}")
-    return theta, losses
-
-
-def predict_linear_regression(X, theta):
-    """Predict using learned linear model."""
-    X_b = np.hstack([np.ones((X.shape[0], 1)), X])
-    return X_b @ theta
-
-
-def evaluate_model(y_true, y_pred):
-    """Evaluate using sklearn's built-in MSE and R² functions."""
-    mse = mean_squared_error(y_true, y_pred)
-    r2 = r2_score(y_true, y_pred)
-    return mse, r2

preprocessing.py

@@ -1,26 +0,0 @@
-import numpy as np
-from sklearn.preprocessing import MinMaxScaler
-from sklearn.model_selection import train_test_split
-
-
-def scale_data(data):
-    """Normalize the data using MinMaxScaler."""
-    scaler = MinMaxScaler()
-    scaled_data = scaler.fit_transform(data)
-    return scaled_data, scaler
-
-
-def inverse_scale(scaled, scaler, n_features):
-    """Inverse transform using stored scaler."""
-    return scaler.inverse_transform(scaled.reshape(-1, n_features))
-
-
-def create_sequences(data, seq_length):
-    """Transform the time series into overlapping sequences."""
-    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)

sklearn_port.py

@@ -4,40 +4,11 @@ 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.linear_model import LinearRegression
+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 global_config import DATA_FILE_NAME
-DATA_FILE_NAME = "hanoi_weather_data.csv"
+from load_data import cut_headers
-
-# from load_data import cut_headers
-
-import io
-
-# from itertools import islice
-from typing import Union
-
-def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
-    headers = []
-    exist_startheader = False
-
-    while line := stream.readline():
-        if "-BEGIN HEADER-" in line and not exist_startheader:
-            exist_startheader = True
-            headers.append(str(line.strip()))
-        elif "-END HEADER-" in line and exist_startheader:
-            headers.append(str(line.strip()))
-            break
-        elif exist_startheader:
-            # print(f"{line = }")
-            headers.append(str(line.strip()))
-        elif not exist_startheader:
-            continue
-    if not exist_startheader:
-        # If no headers are found, reset the stream and return
-        stream.seek(0)
-        return "", stream
-    return "\n".join(headers), stream
 
 # 1. Load data
 
@@ -74,10 +45,16 @@ 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)
+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 = LinearRegression()
+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
@@ -96,15 +73,13 @@ predictions_rescaled = scaler.inverse_transform(predictions.reshape(-1, data.sha
 y_test_rescaled = scaler.inverse_transform(y_test.reshape(-1, data.shape[1]))
 
 # 9. Plot results
-
+for i, column in enumerate(data.columns):
-# Loss bar
+    plt.figure(figsize=(10, 5))
-
+    plt.plot(y_test_rescaled[:, i], label=f"Actual {column}")
-
+    plt.plot(predictions_rescaled[:, i], label=f"Predicted {column}")
-# Prediction vs Actual
+    plt.title(f"Actual vs. Predicted for {column}")
-plt.plot(y_test_rescaled, label="Actual")
+    plt.xlabel("Sample")
-plt.plot(predictions_rescaled, label="Predicted")
+    plt.ylabel("Value")
-plt.title("Actual vs. Predicted")
+    plt.legend()
-plt.xlabel("Sample")
+    plt.tight_layout()
-plt.ylabel("Value")
+    plt.show()
-plt.legend()
-plt.show()

visualize.py

@@ -1,137 +0,0 @@
-import matplotlib.pyplot as plt
-import numpy as np
-
-
-def plot_predictions(date_test, y_test_rescaled, predictions_rescaled):
-    plt.figure(figsize=(12, 6))
-    plt.plot(date_test, y_test_rescaled[:, 0], label="Actual")
-    plt.plot(date_test, predictions_rescaled[:, 0], label="Predicted")
-    plt.title("Actual vs Predicted (First Feature)")
-    plt.xlabel("Date")
-    plt.ylabel("Value")
-    plt.xticks(rotation=45)
-    plt.legend()
-    plt.tight_layout()
-    plt.grid(True)
-    plt.show()
-
-
-def plot_residuals(date_test, residuals):
-    plt.figure(figsize=(10, 4))
-    plt.plot(date_test, residuals, label="Residuals")
-    plt.hlines(0, 0, len(residuals), colors="red")
-    plt.xlim(date_test.min(), date_test.max())
-    plt.title("Residuals Over Time")
-    plt.xlabel("Date")
-    plt.ylabel("Error")
-    plt.xticks(rotation=45)
-    plt.grid(True)
-    plt.tight_layout()
-    plt.legend()
-    plt.show()
-
-
-def plot_error_hist(errors):
-    plt.hist(errors, bins=50)
-    plt.title("Error Distribution")
-    plt.xlabel("Absolute Error")
-    plt.ylabel("Frequency")
-    plt.grid(True)
-    plt.show()
-
-
-def plot_scatter(y_test, predictions):
-    plt.scatter(y_test[:, 0], predictions[:, 0], alpha=0.5)
-    plt.plot([0, 1], [0, 1], "r--")
-    plt.title("Predicted vs Actual (Normalized)")
-    plt.xlabel("Actual")
-    plt.ylabel("Predicted")
-    plt.grid(True)
-    plt.show()
-
-
-def plot_loss_curve(losses):
-    plt.plot(losses)
-    plt.title("Training Loss Curve")
-    plt.xlabel("Epoch")
-    plt.ylabel("MSE Loss")
-    plt.grid(True)
-    plt.tight_layout()
-    plt.show()
-
-
-def plot_original_vs_scaled(original_data, scaled_data, feature_names=None):
-    """
-    Plot original and scaled data, aligned by date.
-    """
-    if feature_names is None:
-        feature_names = original_data.columns[:2]
-
-    dates = original_data.index  # Grab the datetime index
-
-    fig, axs = plt.subplots(2, 1, figsize=(12, 6), sharex=True)
-
-    for col in feature_names:
-        axs[0].plot(dates, original_data[col], label=f"Original {col}")
-    axs[0].set_title("Original Data")
-    axs[0].legend()
-    axs[0].grid(True)
-
-    for i, col in enumerate(feature_names):
-        col_index = original_data.columns.get_loc(col)
-        axs[1].plot(dates, scaled_data[:, col_index], label=f"Scaled {col}")
-    axs[1].set_title("Scaled Data (MinMaxScaler)")
-    axs[1].legend()
-    axs[1].grid(True)
-
-    plt.xlabel("Date")
-    plt.tight_layout()
-    plt.show()
-
-
-def plot_value_distribution(data):
-    # import matplotlib.pyplot as plt
-
-    plt.figure(figsize=(8, 4))
-    plt.hist(data.iloc[:, 0], bins=40, color="skyblue", edgecolor="black")
-    plt.title("Distribution of Values")
-    plt.xlabel(data.columns[0])
-    plt.ylabel("Frequency")
-    plt.grid(True)
-    plt.tight_layout()
-    plt.show()
-
-
-def visualize_sequence_window(series, seq_length=5, start_idx=0):
-    """
-    Visualize how a sequence window is used to create X (input) and y (target).
-
-    Parameters:
-        series (pd.Series or np.ndarray): 1D time series data
-        seq_length (int): Length of input window
-        start_idx (int): Where to start slicing from for demo
-    """
-    if isinstance(series, np.ndarray):
-        data = series
-    else:
-        data = series.to_numpy()
-
-    x_seq = data[start_idx:start_idx + seq_length]
-    y_val = data[start_idx + seq_length]
-
-    full_seq = np.concatenate([x_seq, [y_val]])
-
-    plt.figure(figsize=(8, 3))
-    plt.plot(range(start_idx, start_idx + seq_length + 1), full_seq, marker='o')
-    plt.axvline(x=start_idx + seq_length - 0.5, linestyle="--", color="gray")
-
-    for i in range(seq_length):
-        plt.text(start_idx + i, x_seq[i], f"x[{i}]", ha="center", va="bottom", fontsize=9)
-    plt.text(start_idx + seq_length, y_val, "y", ha="center", va="bottom", color="red", fontsize=9)
-
-    plt.title(f"Sequence Window (seq_length={seq_length}) → Predict Next")
-    plt.xlabel("Time Step")
-    plt.ylabel("Value")
-    plt.grid(True)
-    plt.tight_layout()
-    plt.show()