import matplotlib.pyplot as plt
import pandas as pd
import array as arr
# Importing the dataset
dataset = pd.read_csv('Potential datasets for recruitment (Trip).csv')
a = [0,1,2,3,5,6,7,8,9,10,11,12,13,14,15,17,18,19]
X = dataset.iloc[:, a].values
y = dataset.iloc[:, 4].values

i = 0
while(i<504):
    if(X[i][13]=='3,5'):
        X[i][13]='4'
        i = i + 1
    elif(X[i][13]=='4,5'):
        X[i][13]='4.5'
        i = i + 1
    else:
        i = i + 1


# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 0] = labelencoder_X_1.fit_transform(X[:, 0])
labelencoder_X_2 = LabelEncoder()
X[:, 4] = labelencoder_X_2.fit_transform(X[:, 4])
labelencoder_X_3 = LabelEncoder()
X[:, 5] = labelencoder_X_1.fit_transform(X[:, 5])
labelencoder_X_4 = LabelEncoder()
X[:, 6] = labelencoder_X_1.fit_transform(X[:, 6])
labelencoder_X_5 = LabelEncoder()
X[:, 7] = labelencoder_X_1.fit_transform(X[:, 7])
labelencoder_X_6 = LabelEncoder()
X[:, 8] = labelencoder_X_1.fit_transform(X[:, 8])
labelencoder_X_7 = LabelEncoder()
X[:, 9] = labelencoder_X_1.fit_transform(X[:, 9])
labelencoder_X_8 = LabelEncoder()
X[:, 10] = labelencoder_X_1.fit_transform(X[:, 10])
labelencoder_X_9 = LabelEncoder()
X[:, 11] = labelencoder_X_1.fit_transform(X[:, 11])
labelencoder_X_10 = LabelEncoder()
X[:, 12] = labelencoder_X_1.fit_transform(X[:, 12])
labelencoder_X_11 = LabelEncoder()
X[:, 16] = labelencoder_X_1.fit_transform(X[:, 16])
labelencoder_X_12 = LabelEncoder()
X[:, 17] = labelencoder_X_1.fit_transform(X[:, 17])
b = [0,4,5,6,7,8,9,10,11,12,16,17]
b = arr.array('b',b)
onehotencoder = OneHotEncoder(categorical_features = b)
X = onehotencoder.fit_transform(X).toarray()

runfile('C:/Users/LENOVO/Desktop/Innovacer/Data Science - Intern/newusingDeepLearning.py', wdir='C:/Users/LENOVO/Desktop/Innovacer/Data Science - Intern')
C:UsersLENOVOAnaconda3libsite-packagessklearnpreprocessing_encoders.py:385: DeprecationWarning: The 'categorical_features' keyword is deprecated in version 0.20 and will be removed in 0.22. You can use the ColumnTransformer instead.
  "use the ColumnTransformer instead.", DeprecationWarning)
Traceback (most recent call last):

  File "<ipython-input-108-7cf5520eeefd>", line 1, in <module>
    runfile('C:/Users/LENOVO/Desktop/Innovacer/Data Science - Intern/newusingDeepLearning.py', wdir='C:/Users/LENOVO/Desktop/Innovacer/Data Science - Intern')

  File "C:UsersLENOVOAnaconda3libsite-packagesspyder_kernelscustomizespydercustomize.py", line 668, in runfile
    execfile(filename, namespace)

  File "C:UsersLENOVOAnaconda3libsite-packagesspyder_kernelscustomizespydercustomize.py", line 108, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "C:/Users/LENOVO/Desktop/Innovacer/Data Science - Intern/newusingDeepLearning.py", line 51, in <module>
    X = onehotencoder.fit_transform(X).toarray()

  File "C:UsersLENOVOAnaconda3libsite-packagessklearnpreprocessing_encoders.py", line 499, in fit_transform
    self._categorical_features, copy=True)

  File "C:UsersLENOVOAnaconda3libsite-packagessklearnpreprocessingbase.py", line 71, in _transform_selected
    X_sel = transform(X[:, ind[sel]])

  File "C:UsersLENOVOAnaconda3libsite-packagessklearnpreprocessing_encoders.py", line 441, in _legacy_fit_transform
    % type(X))

TypeError: Wrong type for parameter `n_values`. Expected 'auto', int or array of ints, got <class 'numpy.ndarray'>