Question

This is my code:

import numpy as np
import pandas as pd
import sys
from keras.models import Sequential
from keras.layers import Dense
from sklearn.preprocessing import StandardScaler
from keras.layers.normalization import BatchNormalization
from keras.layers import Dropout

file_full=pd.read_csv("/Users/anwer/Desktop/copy/FULL.csv")
file_bottom=pd.read_csv("/Users/anwer/Desktop/copy/bottom.csv")
train=[]
train_targets=[]
test=[]
test_targets=[]
p=[]
q=[]

  
# We will generate train data using 50% of full data and 50% of bottom data.
#is train target for labeling ? yes for train data
train_df = file_full[:len(file_full)//2]

labels=[ 0 for i in range(len(file_full)//2)]

train_df=train_df.append(file_bottom[:len(file_bottom)//2])

for i in range(len(file_bottom)//2):

labels.append(1)

train_df['label']=labels

train = train_df.drop('label',axis=1)

train_label= train_df['label']
  
  
test_df = file_full[len(file_full)//2:len(file_full)]

labels2=[ 0 for i in range(len(file_full)//2)]

test_df=test_df.append(file_bottom[len(file_bottom)//2:len(file_bottom)])

for i in range(len(file_bottom)//2):

labels2.append(1)

test_df['label']=labels2

test = test_df.drop('label',axis=1)

test_label= test_df['label']
# Training Model

#can you comment those lines? I want to know what they do?
#train = np.array(train).reshape(-1,1)
scaler = StandardScaler().fit(train)

train=scaler.transform(train)
test=scaler.transform(test)

# Creating Deep Model

model = Sequential()

# Add an input layer
model.add(Dense(12, activation='relu', input_shape=(211,)))

# Add one hidden layer
model.add(Dense(8, activation='relu'))

# Add an output layer
model.add(Dense(1, activation='sigmoid'))

#add improvements
model.add(BatchNormalization())
model.add(Dropout(0.5))
#Train the model

model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])

model.fit(train,train_targets,epochs=20, batch_size=1, verbose=1)

#TEst the model

y_pred = model.predict(test)

# Evaluate the model

score = model.evaluate(test, test_targets,verbose=1)

print(score)

ERROR:

I am getting error at this line:

model.fit(train,train_targets,epochs=20, batch_size=1, verbose=1)

the error is :

File "C:\Users\bob\Anaconda3\lib\site-packages\keras\engine\training_utils.py", line 80, in standardize_input_data
if isinstance(data[0], list):

IndexError: list index out of range.

what is caussing this error and how can I fix it?

Answer 1

in file : C:\Users\bob\Anaconda3\lib\site-packages\keras\engine\training_utils.py

list is one kind of array type so that we can not use it as a list only. it should be something like list[i]. or else.

in isinstance, we should provide int in the second argument. so that there should be integer not list.

try : if isinstance(data[0], list[0]).