Check within a column if a certain value is contained, if yes set a value-CodePudding

I have a problem. I want to run a loop through the whole series and check if it contains a certain value. If this row contains a certain value, it should be set to true. I get the following error: TypeError: 'bool' object does not support item assignment

Dataframe

   customerId                text
0           1  Something with Cat
1           3  That is a huge dog
2           3         Hello agian

Code

import pandas as pd
import copy
import re
d = {
    "customerId": [1, 3, 3],
    "text": ["Something with Cat", "That is a huge dog", "Hello agian"],
}
df = pd.DataFrame(data=d)
my_list = ['cat', 'dog', 'mouse']
def f(x):
    match = False
    for element in my_list:
        x = bool(re.search(element, x['text'], re.IGNORECASE))
        if(x):
            #print(forwarder)
            match = True
            break
    x['test'] = str(match)
    return x
    #print(match)
df['test'] = None
df = df.apply(lambda x: f(x), axis = 1)

What I want

   customerId                text   test
0           1  Something with Cat   True
1           3  That is a huge dog   True
2           3         Hello agian   False

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
File <timed exec>:13, in <module>

File ~\Anaconda3\lib\site-packages\pandas\core\frame.py:8839, in DataFrame.apply(self, func, axis, raw, result_type, args, **kwargs)
   8828 from pandas.core.apply import frame_apply
   8830 op = frame_apply(
   8831     self,
   8832     func=func,
   (...)
   8837     kwargs=kwargs,
   8838 )
-> 8839 return op.apply().__finalize__(self, method="apply")

File ~\Anaconda3\lib\site-packages\pandas\core\apply.py:727, in FrameApply.apply(self)
    724 elif self.raw:
    725     return self.apply_raw()
--> 727 return self.apply_standard()

File ~\Anaconda3\lib\site-packages\pandas\core\apply.py:851, in FrameApply.apply_standard(self)
    850 def apply_standard(self):
--> 851     results, res_index = self.apply_series_generator()
    853     # wrap results
    854     return self.wrap_results(results, res_index)

File ~\Anaconda3\lib\site-packages\pandas\core\apply.py:867, in FrameApply.apply_series_generator(self)
    864 with option_context("mode.chained_assignment", None):
    865     for i, v in enumerate(series_gen):
    866         # ignore SettingWithCopy here in case the user mutates
--> 867         results[i] = self.f(v)
    868         if isinstance(results[i], ABCSeries):
    869             # If we have a view on v, we need to make a copy because
    870             #  series_generator will swap out the underlying data
    871             results[i] = results[i].copy(deep=False)

File <timed exec>:13, in <lambda>(x)

File <timed exec>:9, in f(x)

TypeError: 'bool' object does not support item assignment

CodePudding user response：

What about just using:

df['test'] = df['text'].str.contains('|'.join(my_list), case=False)

Or, if your words might contain special characters:

import re
df['test'] = df['text'].str.contains('|'.join(map(re.escape, my_list)),
                                     case=False)

output:

   customerId                text   test
0           1  Something with Cat   True
1           3  That is a huge dog   True
2           3         Hello agian  False

CodePudding user response：

You can use re.compile and create pattaren you want : cat|dog| mouse then use apply on column text.

import re
my_list = ['cat', 'dog', 'mouse']
pattern = re.compile('|'.join(my_list), re.IGNORECASE)
df['test'] = df['text'].apply(lambda x: True if pattern.search(x) else False)
print(df)

Output:

   customerId                text   test
0           1  Something with Cat   True
1           3  That is a huge dog   True
2           3         Hello agian  False

CodePudding user response：

The x = bool(re.) is duplicated with the x in f(x), you can rename it with another name

def f(x):
    match = False
    for element in my_list:
        y = bool(re.search(element, x['text'], re.IGNORECASE))
        #^ here
        if(y):
            #print(forwarder)
            match = True
            break
    x['test'] = str(match)
    return x