Added tests, made fixes, made changes to OPT OUT streamlit,

Added additional test cases to increase coverage (excluding the ui module). Made minor fixes to the code, and made slight changes to documentation.

.coveragerc

@@ -0,0 +1,8 @@
+[run]
+omit =
+    # omit anything in a .local directory anywhere
+    */.local/*
+    # omit everything in /usr
+    /usr/*
+    # omit the UI folder
+    QuadratiK/ui/*

.gitignore

@@ -158,3 +158,4 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 .vscode/
+htmlcov/

QuadratiK/datasets/_dataset.py

@@ -80,7 +80,9 @@ def load_wireless_data(desc=False, return_X_y=False, as_dataframe=True, scaled=F
     )
 
     if scaled:
-        data = data / np.linalg.norm(data, axis=1, keepdims=True)
+        data[:, :-1] = data[:, :-1] / np.linalg.norm(
+            data[:, :-1], axis=1, keepdims=True
+        )
 
     feature_names = ["WS1", "WS2", "WS3", "WS4", "WS5", "WS6", "WS7", "Class"]
 
@@ -103,3 +105,5 @@ def load_wireless_data(desc=False, return_X_y=False, as_dataframe=True, scaled=F
             return (fdescr, pd.DataFrame(data, columns=feature_names))
         else:
             return pd.DataFrame(data, columns=feature_names)
+    else:
+        return data

QuadratiK/kernel_test/_h_selection.py

@@ -1,5 +1,5 @@
 """
-Contains the tuning parameter selecrtion algorithm
+Contains the tuning parameter selection algorithm
 """
 
 import numpy as np

QuadratiK/kernel_test/_kernel_test.py

@@ -204,9 +204,9 @@ def test(self, x, y=None):
             raise TypeError("x must be a numpy array or a pandas dataframe")
 
         if self.y is not None:
-            if isinstance(self.y, np.ndarray):
+            if isinstance(self.y, (np.ndarray, pd.Series)):
                 if self.y.ndim == 1:
-                    self.y = self.y.reshape(-1, 1)
+                    self.y = np.array(self.y).reshape(-1, 1)
             elif isinstance(y, pd.DataFrame):
                 self.y = self.y.to_numpy()
             else:
@@ -349,13 +349,14 @@ def test(self, x, y=None):
                 return self
 
             else:
+                print("Entered this K Sample Else")
                 if (self.y is not None) and (self.x.shape[0] != self.y.shape[0]):
                     raise ValueError("'x' and 'y' must have the same number of rows.")
 
                 if self.h is None:
                     self.h = select_h(
                         self.x,
-                        y=None,
+                        self.y,
                         alternative=self.alternative,
                         method=self.method,
                         num_iter=self.num_iter,

QuadratiK/kernel_test/_utils.py

@@ -143,8 +143,6 @@ def stat_two_sample(x_mat, y_mat, h, mu_hat, sigma_hat, centering_type="nonparam
         k_center = nonparam_centering(kmat_zz, n_z)
     elif centering_type == "param":
         k_center = param_centering(kmat_zz, z_mat, cov_h, mu_hat, sigma_hat)
-    else:
-        raise ValueError("Unknown centering type.")
     np.fill_diagonal(k_center, 0)
     test_non_par = (
         (np.sum(k_center[:n_x, :n_x]) / (n_x * (n_x - 1)))
@@ -187,8 +185,6 @@ def stat_normality_test(x_mat, h, mu_hat, sigma_hat, centering_type="param"):
         k_center = nonparam_centering(kmat_zz, n_x)
     elif centering_type == "param":
         k_center = param_centering(kmat_zz, x_mat, cov_h, mu_hat, sigma_hat)
-    else:
-        raise ValueError("Unknown centering type.")
     np.fill_diagonal(k_center, 0)
     test_normality = np.sum(k_center) / (n_x * (n_x - 1))
     return test_normality

QuadratiK/spherical_clustering/_pkbc.py

@@ -413,9 +413,5 @@ def stats(self):
                 Dataframe of descriptive statistics
 
         """
-
         summary_stats = stats(self.dat, self.labels_)
-        summary_stats_df = pd.concat(
-            summary_stats.values(), keys=summary_stats.keys(), axis=0
-        )
-        return summary_stats_df
+        return summary_stats

QuadratiK/spherical_clustering/_pkbd.py

@@ -45,9 +45,14 @@ def dpkb(self, x, mu, rho, logdens=False):
             raise ValueError("mu must have length >= 2")
         if isinstance(x, pd.DataFrame):
             x = x.to_numpy()
-        p = x.shape[1]
-        if p < 2:
+
+        if x.ndim == 1:
             raise ValueError("vectors must have length >= 2")
+        else:
+            p = x.shape[1]
+            if p < 2:
+                raise ValueError("vectors must have length >= 2")
+
         if len(mu) != p:
             raise ValueError("vectors and mu must have the same length")
         if (rho >= 1) or (rho < 0):

QuadratiK/tools/graphics.py

@@ -64,7 +64,7 @@ def sphere3d(x, y=None):
             where each row represents the coordinates of a point in
             3D space
 
-        y : numpy.ndarray, list, optional
+        y : numpy.ndarray, list, pandas.series, optional
             The parameter `y` is an optional input that determines the color and
             shape of each data point in the plot. If `y` is not provided, the
             scatter plot will have the default marker symbol and color.
@@ -85,7 +85,14 @@ def sphere3d(x, y=None):
         x = x.to_numpy()
 
     if isinstance(y, pd.DataFrame):
-        y = y.to_numpy()
+        y = y.to_numpy().flatten()
+    elif isinstance(y, pd.Series):
+        y = y.values
+    elif isinstance(y, np.ndarray):
+        if y.ndim == 1:
+            pass
+        elif y.ndim == 2:
+            y = y.flatten()
 
     r = 1
     pi = np.pi
@@ -187,7 +194,14 @@ def plot_clusters_2d(x, y=None):
         x = x.to_numpy()
 
     if isinstance(y, pd.DataFrame):
-        y = y.to_numpy()
+        y = y.to_numpy().flatten()
+    elif isinstance(y, pd.Series):
+        y = y.values
+    elif isinstance(y, np.ndarray):
+        if y.ndim == 1:
+            pass
+        elif y.ndim == 2:
+            y = y.flatten()
 
     fig = plt.figure()
     if y is not None:

QuadratiK/ui/_dashboard.py

@@ -44,6 +44,8 @@ async def main(self):
             "#E5E4E2",
             "--theme.textColor",
             "#0e0e0e",
+            "--browser.gatherUsageStats",
+            "false",
         ]
         sys.exit(stcli.main())
 

doc/source/conf.py

@@ -8,14 +8,16 @@
 
 import os
 import sys
-basedir = os.path.abspath(os.path.join(
-    os.path.dirname(__file__), '..', '..'))
+
+basedir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
 sys.path.insert(0, basedir)
 
-project = 'QuadratiK'
-copyright = '2023, Giovanni Saraceno, Marianthi Markatou, Raktim Mukhopadhyay, Mojgan Golzy'
-author = 'Giovanni Saraceno, Marianthi Markatou, Raktim Mukhopadhyay, Mojgan Golzy'
-release = '1.0.0'
+project = "QuadratiK"
+copyright = (
+    "2023, Giovanni Saraceno, Marianthi Markatou, Raktim Mukhopadhyay, Mojgan Golzy"
+)
+author = "Giovanni Saraceno, Marianthi Markatou, Raktim Mukhopadhyay, Mojgan Golzy"
+release = "1.0.0"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
@@ -29,24 +31,29 @@
     "sphinx.ext.githubpages",
     "nbsphinx",
     "sphinx.ext.intersphinx",
-    "myst_parser"
+    "myst_parser",
 ]
 
-templates_path = ['_templates']
+templates_path = ["_templates"]
 exclude_patterns = []
 
 
 # -- Options for HTML output -------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
-html_theme = 'sphinx_book_theme'
-html_static_path = ['_static']
-html_css_files = ['css/custom.css']
+html_theme = "sphinx_book_theme"
+html_static_path = ["_static"]
+html_css_files = ["css/custom.css"]
 strip_signature_backslash = True
 
 # -- Options for Latex output -------------------------------------------------
-latex_elements = {
-    'extraclassoptions': 'openany,oneside'
-}
-latex_documents = [('index', 'QuadratiK.tex', 'QuadratiK', author.replace(
-    'Raktim', '\\and Raktim'), 'manual')]
+latex_elements = {"extraclassoptions": "openany,oneside"}
+latex_documents = [
+    (
+        "index",
+        "QuadratiK.tex",
+        "QuadratiK",
+        author.replace("Raktim", "\\and Raktim"),
+        "manual",
+    )
+]

doc/source/user_guide/basic_usage.ipynb

@@ -13,9 +13,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%matplotlib inline \n",
+    "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
+    "\n",
     "np.random.seed(42)\n",
     "import pandas as pd"
    ]
@@ -49,9 +50,9 @@
    "source": [
     "from QuadratiK.kernel_test import KernelTest\n",
     "\n",
-    "data = np.random.randn(100,2)\n",
+    "data = np.random.randn(100, 2)\n",
     "\n",
-    "normality_test = KernelTest(h=0.4, centering_type=\"param\",random_state=42).test(data)\n",
+    "normality_test = KernelTest(h=0.4, centering_type=\"param\", random_state=42).test(data)\n",
     "print(\"Test : {}\".format(normality_test.test_type_))\n",
     "print(\"Execution time: {:.3f}\".format(normality_test.execution_time))\n",
     "print(\"H0 is Rejected : {}\".format(normality_test.h0_rejected_))\n",
@@ -116,6 +117,7 @@
    "outputs": [],
    "source": [
     "from QuadratiK.tools import qq_plot\n",
+    "\n",
     "qq_plot(data)"
    ]
   },
@@ -141,10 +143,10 @@
    "source": [
     "from QuadratiK.kernel_test import KernelTest\n",
     "\n",
-    "X = np.random.randn(100,2)\n",
-    "Y = np.random.randn(100,2)\n",
+    "X = np.random.randn(100, 2)\n",
+    "Y = np.random.randn(100, 2)\n",
     "\n",
-    "two_sample_test = KernelTest(h=0.4, random_state=42).test(X,Y)\n",
+    "two_sample_test = KernelTest(h=0.4, random_state=42).test(X, Y)\n",
     "print(\"Test : {}\".format(two_sample_test.test_type_))\n",
     "print(\"Execution time: {:.3f}\".format(two_sample_test.execution_time))\n",
     "print(\"H0 is Rejected : {}\".format(two_sample_test.h0_rejected_))\n",
@@ -185,10 +187,11 @@
    "outputs": [],
    "source": [
     "from QuadratiK.kernel_test import KernelTest\n",
-    "X = np.random.randn(500,2)\n",
-    "y = np.random.randint(0,5,500)\n",
     "\n",
-    "k_sample_test = KernelTest(h = 1.5, method = \"permutation\").test(X,y)\n",
+    "X = np.random.randn(500, 2)\n",
+    "y = np.random.randint(0, 5, 500)\n",
+    "\n",
+    "k_sample_test = KernelTest(h=1.5, method=\"permutation\").test(X, y)\n",
     "\n",
     "print(\"Test : {}\".format(k_sample_test.test_type_))\n",
     "print(\"Execution time: {:.3f} seconds\".format(k_sample_test.execution_time))\n",
@@ -232,9 +235,9 @@
     "from QuadratiK.tools import sample_hypersphere\n",
     "from QuadratiK.poisson_kernel_test import PoissonKernelTest\n",
     "\n",
-    "X = sample_hypersphere(100,3, random_state=42)\n",
+    "X = sample_hypersphere(100, 3, random_state=42)\n",
     "\n",
-    "unif_test = PoissonKernelTest(rho = 0.7, random_state=42).test(X)\n",
+    "unif_test = PoissonKernelTest(rho=0.7, random_state=42).test(X)\n",
     "\n",
     "print(\"Execution time: {:.3f} seconds\".format(unif_test.execution_time))\n",
     "\n",
@@ -273,7 +276,7 @@
    "source": [
     "from QuadratiK.tools import qq_plot\n",
     "\n",
-    "qq_plot(X,dist = \"uniform\")"
+    "qq_plot(X, dist=\"uniform\")"
    ]
   },
   {
@@ -348,7 +351,7 @@
     "plt.show()\n",
     "\n",
     "fig = plt.figure(figsize=(6, 4))\n",
-    "plt.plot(list(range(2,10)),wcss_cos, \"--o\")\n",
+    "plt.plot(list(range(2, 10)), wcss_cos, \"--o\")\n",
     "plt.xlabel(\"Number of Cluster\")\n",
     "plt.ylabel(\"Within Cluster Sum of Squares (WCSS)\")\n",
     "plt.title(\"Elbow Plot for Wireless Indoor Localization dataset\")\n",
@@ -369,8 +372,9 @@
    "outputs": [],
    "source": [
     "from QuadratiK.spherical_clustering import PKBD\n",
-    "pkbd_data = PKBD().rpkb(10,[0.5,0],0.5, \"rejvmf\", random_state= 42)\n",
-    "dens_val  = PKBD().dpkb(pkbd_data, [0.5,0.5],0.5)\n",
+    "\n",
+    "pkbd_data = PKBD().rpkb(10, [0.5, 0], 0.5, \"rejvmf\", random_state=42)\n",
+    "dens_val = PKBD().dpkb(pkbd_data, [0.5, 0.5], 0.5)\n",
     "print(dens_val)"
    ]
   },
@@ -401,7 +405,8 @@
     "y = np.random.randint(0, 2, 200)\n",
     "\n",
     "h_selected, all_values, power_plot = select_h(\n",
-    "    X, y, alternative='location', power_plot=True,  random_state=None)\n",
+    "    X, y, alternative=\"location\", power_plot=True, random_state=None\n",
+    ")\n",
     "print(\"Selected h is: \", h_selected)"
    ]
   },
@@ -411,7 +416,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#shows the detailed power vs h table\n",
+    "# shows the detailed power vs h table\n",
     "all_values"
    ]
   },
@@ -421,7 +426,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#shows the power plot\n",
+    "# shows the power plot\n",
     "power_plot"
    ]
   }