first refactor - remove VS sln and proj , add notebooks

.github/workflows/unitTests.yml

@@ -12,14 +12,8 @@ jobs:
 
     - name : Install Packages 
       run : |
-        pip install pytest pandas numpy seaborn
-        pip install scikit-learn scipy matplotlib
+        pip install -r requirements.txt
 
     - name : Run unit tests 
       run : |
-        pytest Tests/test_TrajData.py
-        pytest Tests/test_Base.py
-        pytest Tests/test_ContourData.py
-        pytest Tests/test_AsymCalc.py
-        pytest Tests/test_Clustering.py
-        pytest MLexamples/Tests/test_Regression.py
+        pytest

.gitignore

@@ -0,0 +1,12 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+.pytest_cache/
+.venv/
+.venv-test/
+venv/
+.ipynb_checkpoints/
+*.out
+
+# Generated by running the clustering tests/examples locally
+Data/Clustering/

README.md

@@ -3,3 +3,24 @@
 - Plotting algorithms
 - ML learning tools
 - Unit tests for modules
+
+## Setup
+
+```
+pip install -r requirements.txt
+```
+
+## Tests
+
+Run the full test suite with pytest from the repository root:
+
+```
+pytest
+```
+
+## Examples
+
+`notebooks/examples.ipynb` consolidates the example scripts (clustering, trajectory
+plotting, regression, IRIS, MNIST, ARC asymmetry, contour plotting) and calls the
+underlying helper classes in `Source/` and `MLexamples/`. Some examples require
+data files that aren't included in this repository — see the notes in each section.

Source/Base/BaseDataHelper.py

@@ -1,36 +1,36 @@
-import string
-from numpy import ndarray, void, loadtxt
-from pandas import DataFrame
 import os
+from dataclasses import dataclass, field
+from numpy import ndarray, loadtxt
+from pandas import DataFrame
 
 
+@dataclass(kw_only=True)
 class BaseDataHelper:
     """For importing and manipulating file data"""
-    myDataFrame: DataFrame
-    myArray: ndarray
-
-    def __init__(self, _path: string, _fname: string):
-        self.path = _path
-        self.filename = _fname
+    path: str
+    filename: str
+    my_data_frame: DataFrame = field(init=False, default=None)
+    my_array: ndarray = field(init=False, default=None)
 
-    def CreateDataFrame(self):
-        df = DataFrame(self.myArray)
-        self.myDataFrame = df
+    def create_data_frame(self):
+        if self.my_array is None:
+            raise ValueError("my_array is empty - call load_to_array() first")
+        self.my_data_frame = DataFrame(self.my_array)
 
-    def GetDataFrame(self):
-        return self.myDataFrame
+    def get_data_frame(self):
+        return self.my_data_frame
 
-    def GetFilePath(self) -> string:
+    def get_file_path(self) -> str:
         return self.path + self.filename
 
-    def LoadToArray(self) -> void:
-        cwd = os.getcwd()
-        filePath = BaseDataHelper.GetFilePath(self)
-        self.myArray = loadtxt(cwd + filePath)
+    def load_to_array(self) -> None:
+        file_path = os.path.normpath(os.getcwd() + self.get_file_path())
+        if not os.path.isfile(file_path):
+            raise FileNotFoundError(f"data file not found: {file_path}")
+        self.my_array = loadtxt(file_path)
 
-    def TruncateArray(self, size: int) -> void:
-        newArray = self.myArray[:size]
-        self.myArray = newArray
+    def truncate_array(self, size: int) -> None:
+        self.my_array = self.my_array[:size]
 
-    def GetArray(self) -> ndarray:
-        return self.myArray
+    def get_array(self) -> ndarray:
+        return self.my_array

Source/Base/BasePlotter.py

@@ -14,7 +14,7 @@ def __init__(self, _helper: BaseDataHelper):
         self.helper = _helper
 
     def plotScatter(self, col1: string, col2: string, title="", fontsize=10, pointsize=0.001, save=False):
-        df = self.helper.GetDataFrame()
+        df = self.helper.get_data_frame()
         dfOrbit = df[self.helper.orbit]
         Xarray = np.asarray(df[col1])
         Yarray = np.asarray(df[col2])
@@ -33,7 +33,7 @@ def plotScatter(self, col1: string, col2: string, title="", fontsize=10, pointsi
         matplotlib.pyplot.close()
 
     def plot2Scatter(self, col1: string, col2: string, col3: string, col4: string, title="", fontsize=10, pointsize=0.001, save=False):
-        df = self.helper.GetDataFrame()
+        df = self.helper.get_data_frame()
         Xarray = np.asarray(df[col1])
         Yarray = np.asarray(df[col2])
         X2array = np.asarray(df[col3])
@@ -59,9 +59,9 @@ def PlotColourMesh(self, title=""):
                 'size': 10}
         matplotlib.rc('font', **font)  # increase all font size
         fig, ax = plt.subplots(1, 1, figsize=(14, 8))
-        XRESI = self.helper.XRESI
-        YRESI = self.helper.YRESI
-        ZRESI = self.helper.ZRESI
+        XRESI = self.helper.x_resi
+        YRESI = self.helper.y_resi
+        ZRESI = self.helper.z_resi
         _min = self.helper.min
         _max = self.helper.max
         ax.pcolormesh(XRESI, YRESI, ZRESI, norm=LogNorm(vmin=_min, vmax=_max),\
@@ -71,14 +71,15 @@ def PlotColourMesh(self, title=""):
         plt.show()
 
     def plotSeaborn(self, title: string = "", save: bool = False) -> np.void:
-        df = self.helper.GetDataFrame()
+        df = self.helper.get_data_frame()
         sns.color_palette("pastel")
         sns.pairplot(df, hue='orbit', kind="reg", plot_kws=dict(scatter_kws=dict(s=0.1)), height=1.5)
         self.SaveOrShow(save, title)
 
     def SaveOrShow(self, save: bool, title: string) -> np.void:
         if save is True:
             cwd = os.getcwd()
-            plt.savefig(cwd + self.helper.path + title + ".png")
-        else:
-            plt.show()
+            outputDir = cwd + self.helper.path
+            os.makedirs(outputDir, exist_ok=True)
+            plt.savefig(outputDir + title + ".png")
+        plt.show()