Counting Mulitple Values in a Python pandas Dataframe Column

def ffill_cols(df, cols_to_fill_name='Unn'):
    """
    Forward fills column names. Propagate last valid column name forward to next invalid column. Works similarly to pandas
    ffill().
    
    :param df: pandas Dataframe; Dataframe
    :param cols_to_fill_name: str; The name of the columns you would like forward filled. Default is 'Unn' as
    the default name pandas gives unnamed columns is 'Unnamed'
    
    :returns: list; List of new column names
    """
    cols = df.columns.to_list()
    for i, j in enumerate(cols):
        if j.startswith(cols_to_fill_name):
            cols[i] = cols[i-1]
    return cols

import numpy as np
import pandas as pd   
from IPython.display import display_html 

df1 = pd.DataFrame(np.arange(12).reshape((3,4)),columns=['A','B','C','D',])
df2 = pd.DataFrame(np.arange(16).reshape((4,4)),columns=['A','B','C','D',])

df1_styler = df1.style.set_table_attributes("style='display:inline'").set_caption('Caption table 1')
df2_styler = df2.style.set_table_attributes("style='display:inline'").set_caption('Caption table 2')

display_html(df1_styler._repr_html_()+df2_styler._repr_html_(), raw=True)

import pandas as pd
	
df_1 = pd.DataFrame(
	[['Somu', 68, 84, 78, 96],
	['Kiku', 74, 56, 88, 85],
	['Ajit', 77, 73, 82, 87]],
	columns=['name', 'physics', 'chemistry','algebra','calculus'])

df_2 = pd.DataFrame(
	[['Amol', 72, 67, 91, 83],
	['Lini', 78, 69, 87, 92]],
	columns=['name', 'physics', 'chemistry','science','calculus'])	

frames = [df_1, df_2]

#append dataframes
df = df_1.append(df_2, ignore_index=True, sort=False)

#print dataframe
print("df_1\n------\n",df_1)
print("\ndf_2\n------\n",df_2)
print("\ndf\n--------\n",df)

# function to replace rows in the provided column of the provided dataframe
# that match the provided string above the provided ratio with the provided string
def replace_matches_in_column(df, column, string_to_match, min_ratio = 47):
    # get a list of unique strings
    strings = df[column].unique()
    
    # get the top 10 closest matches to our input string
    matches = fuzzywuzzy.process.extract(string_to_match, strings, 
                                         limit=10, scorer=fuzzywuzzy.fuzz.token_sort_ratio)

    # only get matches with a ratio > 90
    close_matches = [matches[0] for matches in matches if matches[1] >= min_ratio]

    # get the rows of all the close matches in our dataframe
    rows_with_matches = df[column].isin(close_matches)

    # replace all rows with close matches with the input matches 
    df.loc[rows_with_matches, column] = string_to_match
    
    # let us know the function's done
    print("All done!")

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename)) 

df['SettlementDate'] = pd.TimedeltaIndex(df['SettlementDate'], unit='d') + dt.datetime(1900,1,1)

df['Tags'].str.split(expand=True).stack().value_counts()

def weighted_median(df, median_col, weight_col):
    df_sorted = df.sort_values(median_col)
    cumsum = df_sorted[weight_col].cumsum()
    cutoff = df_sorted[weight_col].sum()/2
    return df_sorted[cumsum >= cutoff][median_col].iloc[0]

df.groupby('cluster', group_keys=False).apply(lambda df: df.sample(1))

#--------------install pytorch geometric
!python -c "import torch; print(torch.version.cuda)"
!python -c "import torch; print(torch.__version__)"
# check above version and edit below accordingly

!pip install torch==1.9.0
!pip uninstall -y torch-scatter
!pip uninstall -y torch-sparse
!pip uninstall -y torch-cluster
!pip uninstall -y torch-geometric
!pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.9.0+cu102.html
!pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.9.0+cu102.html
!pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.9.0+cu102.html
!pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.9.0+cu102.html
!pip install torch-geometric

#--------------mount drive-------------------
from google.colab import drive
drive.mount('/content/drive')
### File path
TRAIN_ID_PATH = '/content/drive/MyDrive/folder/pytorch/train.csv'

df.isnull().sum()

#check where is null in a columns
df[df["Business Description"].isnull() == True]

is_NaN = df.isnull()
row_has_NaN = is_NaN.any(axis=1)
rows_with_NaN = df[row_has_NaN]

print(rows_with_NaN)

df['line'].iloc[:2981] = 'train'
df['line'].iloc[2982:] = 'test'

with open('job_post_01.txt', 'a') as f:
    dfAsString = df.to_string(header=False, index=True)
    f.write(dfAsString)

f.close()

data = pd.read_csv('job_post_01.csv')
df = data.sample(frac = 1).reset_index(drop = True)
doc_name_list = df.values.tolist()
doc_train_list = df.iloc[:2981].values.tolist()
doc_test_list = df.iloc[2982:].values.tolist()

# remove punc, segment and stopword
def punc_jieba(text, sep = ' '):
#     stopword = stopwords(["zh"])
    text_punc = re.sub("[\s+\>\<\:\?\.\!\/_,$%^*(+\"\']+|[+——！，。？、~@#￥%……&*（）！，❤。～《》：（）【】「」？”“；：、【】╮╯▽╰╭★→「」]+".encode().decode("utf8"),
                        "",text)
    text_cut = sep.join(jieba.cut(text_punc, cut_all=False)).lower()
#     tokens = word_tokenize(text_cut)
#     clean_text = [word for word in tokens if not word in stopword]
    
    return text_cut
# mothod1
def stop_word(text):
    stopword = stopwords(['zh'])
    remove_stw = [word for word in text if not word in stopword]
    return remove_stw
df['text'] = df['text'].apply(stop_word)
# mothod2
stopword = stopwords(['zh'])
df['text'] = df['text'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stopword)]))

sudo pip install opencc
# if nt work, should clone project first

import pandas as pd
import numpy as np
# -*- coding: utf-8 -*-
import opencc
from opencc import OpenCC

df = pd.read_csv('training.csv').astype(str)

def tra_sim(text):
    cc = OpenCC('tw2s')
    sim = cc.convert(text)
    return sim
df['sim_label'] = df['label'].apply(tra_sim)
df['sim_detail_label'] = df['detail_label'].apply(tra_sim)
df['sim_text'] = df['text'].apply(tra_sim)

%%bash
!sh ./textcleaner.sh