深度学习中的输入数据缩放问题

Question

I am trying to make a project for predicting cancer detection using CSV file data and I have taken the cancer CSV data into 2 files as the name of X_data.csv and Y_data.csv . Please concern below code who are interesting to help me for making the solutions of the problems,

import all needed libraries and sublibraries:

import tensorflow as tf

import keras.backend as K
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
from keras.callbacks import EarlyStopping
from keras.utils import to_categorical
import keras

import numpy as np

from keras.layers import BatchNormalization
from keras.layers import Dropout
from keras import regularizers

import pandas as pd

import sklearn
from sklearn import preprocessing
from sklearn.model_selection import train_test_split

import matplotlib
from matplotlib import pyplot as plt
%matplotlib inline
%config InlineBackend.figure_format='retina'

Import input (x) and output (y) data, and asign these to df1 and df2:

df1 = pd.read_csv('X_data.csv')
df2 = pd.read_csv('Y_data.csv')

Scale input data:

df1 = preprocessing.scale(df1)    //I faced error here

Scaling error is given below:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-3-aec70d746687> in <module>
      1 # Scale input data
      2 
----> 3 df1 = preprocessing.scale(df1)

~/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~/anaconda3/lib/python3.8/site-packages/sklearn/preprocessing/_data.py in scale(X, axis, with_mean, with_std, copy)
    139 
    140     """  # noqa
--> 141     X = check_array(X, accept_sparse='csc', copy=copy, ensure_2d=False,
    142                     estimator='the scale function', dtype=FLOAT_DTYPES,
    143                     force_all_finite='allow-nan')

~/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~/anaconda3/lib/python3.8/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, estimator)
    597                     array = array.astype(dtype, casting="unsafe", copy=False)
    598                 else:
--> 599                     array = np.asarray(array, order=order, dtype=dtype)
    600             except ComplexWarning:
    601                 raise ValueError("Complex data not supported\n"

~/anaconda3/lib/python3.8/site-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 

ValueError: could not convert string to float: 'discrete'

Answer 1

The last line literally says what's the problem. ValueError: could not convert string to float: 'discrete' . If you print your data ( df1.head() ) you'll see there're some string data like the error suggests which the preprocessing function can't handle .

So you must perform data cleaning first (convert string to int/float, handle any missing data, etc.). You may lookout for something like LabelEncoder() function from sklearn or one hot encoder to take care of your string to int issue.