Error:
Traceback (most recent call last):
  File "D:/Clustering/text-cluster-master/similarity.py", line 68, in <module>
    y = X.Articles.copy()
  File "D:\Python3.8.0\Python\lib\site-packages\pandas\core\generic.py", line 5460, in __getattr__
    return object.__getattribute__(self, name)
AttributeError: 'DataFrame' object has no attribute 'Articles'

y = X.Articles.copy()
X.drop(['Articles'], axis=1, inplace=True)

X = pd.read_csv(r"D:\\Clustering\\text-cluster-master\\Articles.csv", error_bad_lines=False)
X.head()

Error:
AttributeError: 'DataFrame' object has no attribute 'Articles'

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib

from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.decomposition import PCA
from sklearn.neighbors import KNeighborsClassifier


matplotlib.style.use('ggplot') # Look Pretty


def plotDecisionBoundary(model, X, y):
  fig = plt.figure()
  ax = fig.add_subplot(111)

  padding = 0.6
  resolution = 0.0025
  colors = ['royalblue','forestgreen','ghostwhite']

  # Calculate the boundaris
  x_min, x_max = X[:, 0].min(), X[:, 0].max()
  y_min, y_max = X[:, 1].min(), X[:, 1].max()
  x_range = x_max - x_min
  y_range = y_max - y_min
  x_min -= x_range * padding
  y_min -= y_range * padding
  x_max += x_range * padding
  y_max += y_range * padding


  xx, yy = np.meshgrid(np.arange(x_min, x_max, resolution),
                       np.arange(y_min, y_max, resolution))


  Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
  Z = Z.reshape(xx.shape)

  # Plot the contour map
  cs = plt.contourf(xx, yy, Z, cmap=plt.cm.terrain)

  # Plot the test original points as well...
  for label in range(len(np.unique(y))):
    indices = np.where(y == label)
    plt.scatter(X[indices, 0], X[indices, 1], c=colors[label], label=str(label), alpha=0.8)

  p = model.get_params()
  plt.axis('tight')
  plt.title('K = ' + str(p['n_neighbors']))



X = pd.read_csv(r"D:\\Clustering\\text-cluster-master\\Articles.csv", error_bad_lines=False)
X.head()

y = X.Articles.copy()
X.drop(['Articles'], axis=1, inplace=True)



y = y.astype("category").cat.codes


X.fillna(X.mean(), inplace=True)


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33,
                                                    random_state=1)


normaliser = preprocessing.Normalizer().fit(X_train)


X_train_normalised = normaliser.transform(X_train)
X_train = pd.DataFrame(X_train_normalised)

X_test_normalised = normaliser.transform(X_test)
X_test = pd.DataFrame(X_test_normalised)


pca_reducer = PCA(n_components=2).fit(X_train_normalised)

X_train = pca_reducer.transform(X_train_normalised)
X_test = pca_reducer.transform(X_test_normalised)


knn = KNeighborsClassifier(n_neighbors=9)
knn.fit(X_train, y_train)

plotDecisionBoundary(knn, X_train, y_train)


print(knn.score(X_test, y_test))

plt.show()

Anldra12 Wrote:@Larz60+ have a look at the overall codes