Add Working Milestone with Initial Results and Model Inference (#82)

* wip: add function to create stratified train-test split from STFT data

* feat(src): implement working function for dataset B to create ready data from STFT files stft_files and add setup.py for package configuration

* feat(notebook): Update variable names for clarity, remove unused imports, and streamline data processing. Implement data concatenation using pandas concat for efficiency. Add validation steps for Dataset B and improve model training consistency across sensors.

* fix(.gitignore): add rule to ignore egg-info directories and ensure proper formatting

* docs(README): add instructions for running stft.ipynb notebook

* feat(notebook): Add evaluation metrics and confusion matrix visualizations for model predictions on Dataset B. Remove commented-out code and integrate data preparation using create_ready_data function.

---------

Co-authored-by: nuluh <dam.ar@outlook.com>

code/src/ml/model_selection.py

@@ -0,0 +1,57 @@
+import numpy as np
+import pandas as pd
+import os
+from sklearn.model_selection import train_test_split as sklearn_split
+
+
+def create_ready_data(
+    stft_data_path: str,
+    stratify: np.ndarray = None,
+) -> tuple:
+    """
+    Create a stratified train-test split from STFT data.
+
+    Parameters:
+    -----------
+    stft_data_path : str
+        Path to the directory containing STFT data files (e.g. 'data/converted/raw/sensor1')
+    stratify : np.ndarray, optional
+        Labels to use for stratified sampling
+
+    Returns:
+    --------
+    tuple
+        (X_train, X_test, y_train, y_test) - Split datasets
+    """
+    ready_data = []
+    for file in os.listdir(stft_data_path):
+        ready_data.append(pd.read_csv(os.path.join(stft_data_path, file)))
+
+    y_data = [i for i in range(len(ready_data))]
+
+    # Combine all dataframes in ready_data into a single dataframe
+    if ready_data:  # Check if the list is not empty
+        # Use pandas concat function instead of iterative concatenation
+        combined_data = pd.concat(ready_data, axis=0, ignore_index=True)
+
+        print(f"Type of combined data: {type(combined_data)}")
+        print(f"Shape of combined data: {combined_data.shape}")
+    else:
+        print("No data available in ready_data list")
+        combined_data = pd.DataFrame()
+
+    # Store the result in x1a for compatibility with subsequent code
+    X = combined_data
+
+    for i in range(len(y_data)):
+        y_data[i] = [y_data[i]] * ready_data[i].shape[0]
+        y_data[i] = np.array(y_data[i])
+
+    if y_data:
+        # Use numpy concatenate function instead of iterative concatenation
+        y = np.concatenate(y_data, axis=0)
+    else:
+        print("No labels available in y_data list")
+        y = np.array([])
+
+    return X, y