Я пытаюсь кодировать некоторую информацию для чтения в модель машинного обучения, используя следующую
import numpy as np
import pandas as pd
import matplotlib.pyplot as py
Dataset = pd.read_csv('filename.csv', sep = ',')
X = Dataset.iloc[:,:-1].values
Y = Dataset.iloc[:,18].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
однако я получаю сообщение об ошибке
runfile('C:/Users/name/Desktop/Machine Learning/Data preprocessing template.py', wdir='C:/Users/taylorr2/Desktop/Machine Learning')
Traceback (most recent call last):
File "<ipython-input-141-a5d1cd02c2df>", line 1, in <module>
runfile('C:/Users/name/Desktop/Machine Learning/Data preprocessing template.py', wdir='C:/Users/taylorr2/Desktop/Machine Learning')
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
execfile(filename, namespace)
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 87, in execfile
exec(compile(scripttext, filename, 'exec'), glob, loc)
File "C:/Users/name/Desktop/Machine Learning/Data preprocessing template.py", line 8, in <module>
Y = Dataset.iloc[:,18].values
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\pandas\core\indexing.py", line 1310, in __getitem__
return self._getitem_tuple(key)
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\pandas\core\indexing.py", line 1560, in _getitem_tuple
self._has_valid_tuple(tup)
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\pandas\core\indexing.py", line 151, in _has_valid_tuple
if not self._has_valid_type(k, i):
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\pandas\core\indexing.py", line 1528, in _has_valid_type
return self._is_valid_integer(key, axis)
File "C:\Users\name\AppData\Local\Continuum\Anaconda2\lib\site-packages\pandas\core\indexing.py", line 1542, in _is_valid_integer
raise IndexError("single positional indexer is out-of-bounds")
IndexError: single positional indexer is out-of-bounds
Я прочитал здесь вопрос о той же ошибке и попробовал
import numpy as np
import pandas as pd
import matplotlib.pyplot as py
Dataset = pd.read_csv('filename.csv', sep = ',')
table = Dataset.find(id='AlerId')
rows = table.find_all('tr')[1:]
data = [[cell.text for cell in row.find_all('td')] for row in rows]
Dataset1 = pd.DataFrame(data=data, columns=columns)
X = Dataset1.iloc[:,:-1].values
Y = Dataset1.iloc[:,18].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
Однако я думаю, что это могло бы просто смутить меня больше и теперь я в еще большей степени.
Любые предложения?