-
-
Save amankharwal/cfe05afb0e9423e6725cfc2adb52e731 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Define a list of commonly found punctuations | |
punc = ('!', "," ,"\'" ,";" ,"\"", ".", "-" ,"?") | |
vowels=['a','e','i','o','u'] | |
# Define a list of double consecutive vowels which are typically found in Dutch and Afrikaans languages | |
same_consecutive_vowels = ['aa','ee', 'ii', 'oo', 'uu'] | |
consecutive_vowels = [''.join(p) for p in permutations(vowels,2)] | |
dutch_combos = ['ij'] | |
# Create a pre-defined set of features based on the "text" column in order to allow us to characterize the string | |
df['word_count'] = df['text'].apply(lambda x : len(x.split())) | |
df['character_count'] = df['text'].apply(lambda x : len(x.replace(" ",""))) | |
df['word_density'] = df['word_count'] / (df['character_count'] + 1) | |
df['punc_count'] = df['text'].apply(lambda x : len([a for a in x if a in punc])) | |
df['v_char_count'] = df['text'].apply(lambda x : len([a for a in x if a.casefold() == 'v'])) | |
df['w_char_count'] = df['text'].apply(lambda x : len([a for a in x if a.casefold() == 'w'])) | |
df['ij_char_count'] = df['text'].apply(lambda x : sum([any(d_c in a for d_c in dutch_combos) for a in x.split()])) | |
df['num_double_consec_vowels'] = df['text'].apply(lambda x : sum([any(c_v in a for c_v in same_consecutive_vowels) for a in x.split()])) | |
df['num_consec_vowels'] = df['text'].apply(lambda x : sum([any(c_v in a for c_v in consecutive_vowels) for a in x.split()])) | |
df['num_vowels'] = df['text'].apply(lambda x : sum([any(v in a for v in vowels) for a in x.split()])) | |
df['vowel_density'] = df['num_vowels']/df['word_count'] | |
df['capitals'] = df['text'].apply(lambda comment: sum(1 for c in comment if c.isupper())) | |
df['caps_vs_length'] = df.apply(lambda row: float(row['capitals'])/float(row['character_count']),axis=1) | |
df['num_exclamation_marks'] =df['text'].apply(lambda x: x.count('!')) | |
df['num_question_marks'] = df['text'].apply(lambda x: x.count('?')) | |
df['num_punctuation'] = df['text'].apply(lambda x: sum(x.count(w) for w in punc)) | |
df['num_unique_words'] = df['text'].apply(lambda x: len(set(w for w in x.split()))) | |
df['num_repeated_words'] = df['text'].apply(lambda x: len([w for w in collections.Counter(x.split()).values() if w > 1])) | |
df['words_vs_unique'] = df['num_unique_words'] / df['word_count'] | |
df['encode_ascii'] = np.nan | |
for i in range(len(df)): | |
try: | |
df['text'].iloc[i].encode(encoding='utf-8').decode('ascii') | |
except UnicodeDecodeError: | |
df['encode_ascii'].iloc[i] = 0 | |
else: | |
df['encode_ascii'].iloc[i] = 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment