Python Forum

Hi guys i have a twitter dataset i want to train and test with NB and SVM. After cleaning and vectorizing, i am stuck on the following:
1. splitting of data into 80/20
2. fitting this into classifier.

Your guidance will be highly appreciated.

# tokenize helper function
def text_process(raw_text):
   
    # Check  punctuation
    nopunc = [char for char in list(raw_text) if char not in string.punctuation]
    # Join the characters again to form the string.
    nopunc = ''.join(nopunc)
    
    # remove any stopwords
    return [word for word in nopunc.lower().split() if word.lower() not in stopwords.words('english')]

def remove_words(word_list):
    remove = ['he','and','...','“','”','’','…','and’']
    return [w for w in word_list if w not in remove]

# tokenize message column and create a column for tokens
df_marathon = df_marathon.copy()
df_marathon['tokens'] = df_marathon['Text'].apply(text_process) # step 1
df_marathon['tokenized_tweet'] = df_marathon['tokens'].apply(remove_words) # ste 2
df_marathon.head(10)

# vectorize
bow_transformer = CountVectorizer(analyzer=text_process).fit(df_marathon['tokenized_tweet'])
# print total number of vocab words
print(len(bow_transformer.vocabulary_))

# example of vectorized text
sample_tweet = df_marathon['tokenized_tweet'][16]
print(sample_tweet)
print('\n')
# vector representation
bow_sample = bow_transformer.transform([sample_tweet])
print(bow_sample)
print('\n')

# transform the entire DataFrame of messages
X = bow_transformer.transform(df_marathon['Text'])
# check out the bag-of-words counts for the entire corpus as a large sparse matrix
print('Shape of Sparse Matrix: ', X.shape)
print('Amount of Non-Zero occurences: ', X.nnz)

#convert values obtained using the bag of words model into TFIDF values
tfidfconverter = TfidfTransformer()  
X = tfidfconverter.fit_transform(X)

X.toarray()

Error on splitting:

ValueError

Error:Traceback (most recent call last)
~\Anaconda3\envs\Ipython.display\lib\site-packages\scipy\sparse\csr.py in asindices(x)
    243                 if idx_dtype != x.dtype:
--> 244                     x = x.astype(idx_dtype)
    245             except:

ValueError: invalid literal for int() with base 10: 'tokenized_tweet'

During handling of the above exception, another exception occurred:

IndexError                                Traceback (most recent call last)
<ipython-input-37-da320e3c2eee> in <module>
      1 # split data into rain and test, we are creating train set 80% and test set 20%
----> 2 Train_X, Test_X, Train_Y, Test_Y = model_selection.train_test_split(X['tokenized_tweet'],ML_Corpus['label'],test_size=0.2)

~\Anaconda3\envs\Ipython.display\lib\site-packages\scipy\sparse\csr.py in __getitem__(self, key)
    333             row, col = self._index_to_arrays(row, col)
    334 
--> 335         row = asindices(row)
    336         col = asindices(col)
    337         if row.shape != col.shape:

~\Anaconda3\envs\Ipython.display\lib\site-packages\scipy\sparse\csr.py in asindices(x)
    244                     x = x.astype(idx_dtype)
    245             except:
--> 246                 raise IndexError('invalid index')
    247             else:
    248                 return x

IndexError: invalid index

Error on fitting classifier:
ValueError                                Traceback (most recent call last)
<ipython-input-38-6fc83fb90fa2> in <module>
----> 1 classifier = MultinomialNB().fit(X, df_marathon)

~\Anaconda3\envs\Ipython.display\lib\site-packages\sklearn\naive_bayes.py in fit(self, X, y, sample_weight)
    583         self : object
    584         """
--> 585         X, y = check_X_y(X, y, 'csr')
    586         _, n_features = X.shape
    587 

~\Anaconda3\envs\Ipython.display\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    759                         dtype=None)
    760     else:
--> 761         y = column_or_1d(y, warn=True)
    762         _assert_all_finite(y)
    763     if y_numeric and y.dtype.kind == 'O':

~\Anaconda3\envs\Ipython.display\lib\site-packages\sklearn\utils\validation.py in column_or_1d(y, warn)
    795         return np.ravel(y)
    796 
--> 797     raise ValueError("bad input shape {0}".format(shape))
    798 
    799 

ValueError: bad input shape (200, 3)

It would be helpful if you posted the whole thing so it could be tested...

Error:
NameError: name 'df_marathon' is not defined

Jmekubo

michalmonday