show the visualization of the dataset before and after classification - machine-learning

Question

Kindly, I am trying to create an ML model using SVM using a dataset with 23 features and the output should be (0 or 1) which means two classes. My Target to show the visualization before and after the classification.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
ds= pd.read_csv("dataset_sdn.csv")
ds= ds.fillna(0)
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
X_Train, X_Test, Y_Train, Y_Test = train_test_split (X, Y, test_size=0.25, random_state=0)
sc_X = StandardScaler()
X_Train = sc_X.fit_transform(X_Train)
X_Test = sc_X.transform(X_Test)
Then i tried to visualization the X and Y
import matplotlib.pyplot as plt
plt.scatter(X,Y)
plt.show()
But i got error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [11], in <cell line: 2>()
1 import matplotlib.pyplot as plt
----> 2 plt.scatter(X,Y)
3 plt.show()
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\pyplot.py:2817, in scatter(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, data, **kwargs) 2812 #_copy_docstring_and_deprecators(Axes.scatter) 2813 def scatter( 2814 x, y, s=None, c=None, marker=None, cmap=None, norm=None, 2815 vmin=None, vmax=None, alpha=None, linewidths=None, *, 2816 edgecolors=None, plotnonfinite=False, data=None,
**kwargs):
-> 2817 __ret = gca().scatter( 2818 x, y, s=s, c=c, marker=marker, cmap=cmap, norm=norm, 2819 vmin=vmin, vmax=vmax, alpha=alpha, linewidths=linewidths, 2820 edgecolors=edgecolors, plotnonfinite=plotnonfinite, 2821
**({"data": data} if data is not None else {}), **kwargs) 2822 sci(__ret) 2823 return __ret
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\__init__.py:1414, in _preprocess_data.<locals>.inner(ax, data, *args, **kwargs) 1411 #functools.wraps(func) 1412 def inner(ax, *args, data=None,
**kwargs): 1413 if data is None:
-> 1414 return func(ax, *map(sanitize_sequence, args), **kwargs) 1416 bound = new_sig.bind(ax, *args, **kwargs) 1417 auto_label = (bound.arguments.get(label_namer) 1418 or bound.kwargs.get(label_namer))
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\axes\_axes.py:4368, in Axes.scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, **kwargs) 4366 y = np.ma.ravel(y) 4367 if x.size != y.size:
-> 4368 raise ValueError("x and y must be the same size") 4370 if s is None: 4371 s = (20 if rcParams['_internal.classic_mode'] else 4372 rcParams['lines.markersize'] ** 2.0)
ValueError: x and y must be the same size
Then i start the classification
classifier = SVC (kernel='rbf', C=1, random_state=0,)
classifier.fit(X_Train, Y_Train)
Y_pred = classifier.predict(X_Test)
print (Y_pred)
The I tried to use below code but not work
from mlxtend.plotting import plot_decision_regions
plot_decision_regions(X=X_Test, y=Y_Test, clf=classifier, legend=1)
I get this error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [10], in <cell line: 2>()
1 from mlxtend.plotting import plot_decision_regions
----> 2 plot_decision_regions(X=Y_Test, y=X_Test, clf=classifier,legend=2)
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\plotting\decision_regions.py:148, in plot_decision_regions(X, y, clf, feature_index, filler_feature_values, filler_feature_ranges, ax, X_highlight, zoom_factor, legend, hide_spines, markers, colors, scatter_kwargs, contourf_kwargs, contour_kwargs, scatter_highlight_kwargs)
44 def plot_decision_regions(
45 X,
46 y, (...)
65 scatter_highlight_kwargs=None,
66 ):
67 """Plot decision regions of a classifier.
68
69 Please note that this functions assumes that class labels are (...)
145
146 """
--> 148 check_Xy(X, y, y_int=True) # Validate X and y arrays
149 dim = X.shape[1]
151 if ax is None:
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\utils\checking.py:16, in check_Xy(X, y, y_int)
12 def check_Xy(X, y, y_int=True):
13
14 # check types
15 if not isinstance(X, np.ndarray):
---> 16 raise ValueError("X must be a NumPy array. Found %s" % type(X))
17 if not isinstance(y, np.ndarray):
18 raise ValueError("y must be a NumPy array. Found %s" % type(y))
ValueError: X must be a NumPy array. Found <class 'pandas.core.series.Series'>
So, please your advice to how show the visualization. Thanks in advance

Answer 1

See here:
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
and then here
plt.scatter(X,Y)
Your X vector is multi-dimensional vector having a size of 16 and hence the scatterplot is not working. You can only plot 2 variables in a 2D scatterplot.
So you have plot for each feature vs Y, e.g.,
plt.scatter(X.iloc[:,0], Y)