ValueError: Found array with 0 feature(s) (shape=(2698, 0)) while a minimum of 1 is required by MinM-CodePudding

I was trying to use sklearn to do a preprocessing for my data

import math
import datetime
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pandas_datareader import data
import pandas_datareader.data as web

from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, LSTM


start = datetime.datetime(2011,1,1)
end = datetime.date.today()
df = web.DataReader("1211.HK", "yahoo", start, end)

plt.figure(figsize=(16,8))
plt.title('BYD close price',fontsize=18)
plt.plot(df['Close'])
plt.xlabel('Date',fontsize=18)
plt.ylabel('Close price HK($)',fontsize=18)
plt.show()

data = df.filter(['close'])
dataset = data.values
trainning_data_len =math.ceil(len (dataset)*.8)

scaler = MinMaxScaler()
scaled_data = scaler.fit_transform(dataset)

An error was reported when I tried to check the scaled_data

ValueError: Found array with 0 feature(s) (shape=(2698, 0)) while a minimum of 1 is required by MinMaxScaler.

and I have no idea how to solve the problem.
Thanks in advance.

UPDATE: The environment I run is jupyterLab 1.2.6, and following are the log of the error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-9-146c8eeabe3c> in <module>
      1 scaler = MinMaxScaler()
----> 2 scaled_data = scaler.fit_transform(dataset)

/opt/anaconda3/lib/python3.7/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
    569         if y is None:
    570             # fit method of arity 1 (unsupervised transformation)
--> 571             return self.fit(X, **fit_params).transform(X)
    572         else:
    573             # fit method of arity 2 (supervised transformation)

/opt/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/_data.py in fit(self, X, y)
    337         # Reset internal state before fitting
    338         self._reset()
--> 339         return self.partial_fit(X, y)
    340 
    341     def partial_fit(self, X, y=None):

/opt/anaconda3/lib/python3.7/site-packages/sklearn/preprocessing/_data.py in partial_fit(self, X, y)
    371         X = check_array(X,
    372                         estimator=self, dtype=FLOAT_DTYPES,
--> 373                         force_all_finite="allow-nan")
    374 
    375         data_min = np.nanmin(X, axis=0)

/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    592                              " a minimum of %d is required%s."
    593                              % (n_features, array.shape, ensure_min_features,
--> 594                                 context))
    595 
    596     if warn_on_dtype and dtype_orig is not None and array.dtype != dtype_orig:

ValueError: Found array with 0 feature(s) (shape=(2698, 0)) while a minimum of 1 is required by MinMaxScaler.

CodePudding user response：

Your data frame:

Index(['High', 'Low', 'Open', 'Close', 'Volume', 'Adj Close'], dtype='object')

So it should be df.filter(['Close']) instead of df.filter(['close']) :

data = df.filter(['Close'])
dataset = data.values
trainning_data_len =math.ceil(len (dataset)*.8)

scaler = MinMaxScaler()
scaled_data = scaler.fit_transform(dataset)

scaled_data[:5]
array([[0.09673202],
       [0.10424837],
       [0.10441177],
       [0.10571895],
       [0.10571895]])