pandas_basics.py

#!/home/ounis/pyapps/virtual_envs/pandas_test/bin/python


#
# by OuNiS 10.2023
#
#
# https://www.geeksforgeeks.org/data-structures-in-pandas/?ref=shm
# https://pandas.pydata.org/pandas-docs/stable/index.html
# https://stackoverflow.com/questions/16476924/how-to-iterate-over-rows-in-a-dataframe-in-pandas
# https://stackoverflow.com/posts/55557758/revisions
#
#

FILENAME = "/home/ounis/pyapps/mfkig.txt"
FIELDSEP = "="

FIELD1 = "num"
FIELD2 = "name"

FIELDS = [FIELD1, FIELD2]
#
#
'''
file content:
 1=Egmont
 2=Multiversum
 3=Zin Zin Press
 4=Wydawnictwo Kurc
 5=Hanami
 6=Scream
 7=Timof Comics
 ...

 no header with column names, no standard separator
'''

print("Importing modules...")
import pandas as pd

print(FILENAME)

def pressENTER():
    input("ENTER...")

def load_pd(fname, fieldsep):
    print("Loading data...")
    return pd.read_csv(fname, sep=fieldsep, header=None, names=[field for field in FIELDS])

# loading data from file own way
# if the file isn't proper CSV...
def load_own(fname, fieldsep):
    data_temp = {}
    for field in FIELDS:
        data_temp[field] = []
    with open(fname) as file:
         for line in file:
             line = line.rstrip()
             vals = line.split(fieldsep)
             if len(vals) != len(FIELDS):
                 return None
             else:
                 for i, field in enumerate(FIELDS):
                     data_temp[FIELDS[i]].append(vals[i])
    return pd.DataFrame(data_temp)


data = load_own(FILENAME, FIELDSEP)

print("Listing first 25 rows:")
print(data.head(25))
pressENTER()

print("listing first 25 rows sorted by 'name':")
print(data.sort_values(by="name").head(25))
# or
# sort by column number
# print(data.sort_values(data.columns[1]).head(25))

# changing columns/fields names
# manual:
# https://www.geeksforgeeks.org/how-to-rename-columns-in-pandas-dataframe/
pressENTER()
print("Changing columns names\nfrom:")
print(data.columns)
data.rename(columns= {"num": "NUM", "name": "NAME"}, inplace=True)
print("to:")
print(data.columns)
print(data.head(3))