import pandas as pd
# Load the output dataframe
output_df = pd.read_excel('/content/drive/MyDrive/project/Data_Extraction_and_NLP TestAssignment/Output Data Structure.xlsx')
# URL_ID 44, 57, 144 do not exist, drop those rows
output_df.drop([44-37, 57-37, 144-37], axis=0, inplace=True)
# List of variables to assign to dataframe columns
variables = [
positive_score,
negative_score,
polarity_score,
subjectivity_score,
avg_sentence_length,
Percentage_of_Complex_words,
Fog_Index,
avg_sentence_length,
complex_word_count,
word_count,
avg_syllable_word_count,
pp_count,
average_word_length
]
for i, var in enumerate(variables):
output_df.iloc[:,i+2] = var
I was expecting a csv file with all these parameters as output but the output I am getting is and this is the error I get:
ValueError Traceback (most recent call last) in <cell line: 26>() 25 26 for i, var in enumerate(variables): ---> 27 output_df.iloc[:,i+2] = var
2 frames /usr/local/lib/python3.10/dist-packages/pandas/core/indexing.py in _setitem_with_indexer_split_path(self, indexer, value, name) 1848 return self._setitem_with_indexer((pi, info_axis[0]), value[0]) 1849 -> 1850 raise ValueError( 1851 "Must have equal len keys and value " 1852 "when setting with an iterable"
ValueError: Must have equal len keys and value when setting with an iterable