mdpython 0.0.16

MD Python Library

MD Python Library

This package contains high level functions for common Python use cases.

Compare Directories

from mdpython.fileutils import compare  
  
cmp = compare.compare_dirs(r"C:\Users\Dell\OneDrive\Desktop\result_9th",  
                           r"C:\Users\Dell\OneDrive\Desktop\result_9th_v2")  
  
cmp.gen_html_report(r"C:\Users\Dell\OneDrive\Desktop\out.html", ["py", "txt",  
                                                                 "json"])  
  
for fl in cmp.files_only_in_right:  
    if fl.name.endswith("py"):  
        print(fl.absolute())

Menu based app

from datetime import datetime
from random import randint, choice
from mdpython.uiutils import menu_based_app

def show_date():
    print(datetime.now().strftime("%Y-%m-%d"))


def show_time():
    print(datetime.now().strftime("%H:%M:%S"))


def show_date_and_time():
    print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"))


def show_random_number():
    print(randint(1, 100))


def show_random_color():
    print(choice(['red', 'blue', 'green']))


ar = [
    ["Random", "Random Integer", show_random_number],
    ["Random", "Random Color", show_random_color],
    ["Date", "Show Date", show_date],
    ["Date", "Show Time", show_time],
    ["Date", "Show Date and Time", show_date_and_time]
]

menu_based_app.start(ar)

Disk cleanup

from mdpython.fileutils import cleanup

dr = r"C:\Users\Dell\OneDrive\Desktop\result_9th"

info = cleanup.retrieve_info(dr)

print("sorted by time")
for dtl in info.sort_by_time()[:5]:
    print(dtl)

print("\nsorted by size")
for dtl in info.sort_by_size()[:5]:
    print(dtl)

print("\nmodified in last 30 mins")
for dtl in info.modified_within(mins=30)[:5]:
    print(dtl)

print("\nmodified more than 1 day ago")
for dtl in info.modified_before(mins=24 * 60)[:5]:
    print(dtl)

print("\nsorted by number of files in directory")
for dtl in info.sort_by_file_count()[:5]:
    print(dtl)

Getting execution duration

from mdpython.debugutils import timer
from random import randint
from math import factorial

timer.start("main")

def count_elements_in_array():
    ar = list(range(randint(1000000,10000000)))
    print(len(ar))

def get_factorial():
    for i in range(5):
        timer.start("looptest")
        num = randint(900,1000)
        print(num, factorial(num))
        timer.stop("looptest")

timer.start("func1")
count_elements_in_array()
timer.stop("func1")

get_factorial()

timer.stop("main")

timer.show()

-- Output
Name                           Duration             Start Time           End Time            
============================== ==================== ==================== ====================
main                           0:00:00.046207       2024-04-08 21:24:59  2024-04-08 21:24:59 
func1                          0:00:00.033129       2024-04-08 21:24:59  2024-04-08 21:24:59 
looptest.4                     0:00:00.010020       2024-04-08 21:24:59  2024-04-08 21:24:59 
looptest.2                     0:00:00.003058       2024-04-08 21:24:59  2024-04-08 21:24:59 
looptest.1                     0:00:00              2024-04-08 21:24:59  2024-04-08 21:24:59 
looptest.3                     0:00:00              2024-04-08 21:24:59  2024-04-08 21:24:59 
looptest.5                     0:00:00              2024-04-08 21:24:59  2024-04-08 21:24:59 

Print current position

from mdpython.debugutils import curpos
from random import randint
from math import factorial


def count_elements_in_array():
    ar = list(range(randint(1000000, 10000000)))
    print(len(ar))


def get_factorial():
    for i in range(5):
        num = randint(900, 1000)
        print(num, factorial(num))
        curpos.show()


count_elements_in_array()
curpos.show()

get_factorial()

Compare Files

from mdpython.fileutils import compare

compare.compare_files(r"C:\Users\Dell\OneDrive\Desktop\spark\b.py",
                      r"C:\Users\Dell\OneDrive\Desktop\spark\c.py",
                      r"C:\Users\Dell\OneDrive\Desktop\spark\out.html")

Track package changes

from mdpython.debugutils import version

version.save("app_dev", r"D:\data\version")
version.timeline("app_dev", r"D:\data\version")
version.compare("app_dev", r"D:\data\version")

Search for functions

import pandas as pd
from mdpython.debugutils import find

a = [1,2]
b = {"k": 1}
s = pd.Series(range(10))

find.search_function(pd, "")
find.list_elements(s, "truncate", showdoc=True)

Flatten JSON

from mdpython.datautils import jsonutil
import json

json_data = {
    "name": "John",
    "age": 30,
    "car": {
        "make": "Toyota",
        "model": "Camry"
    },
    "colors": ["red", "blue", "green"],
    "nested_list": [
        [1, 2, 3],
        {"hello": "world"},
        [[7, 8], [9, 10]],
        [[[11, 12], [13, 14]], [[], [17, 18]]]
    ],
    "nested_dict": {
        "info1": {"key1": "value1"},
        "info2": {"key2": "value2"}
    },
    "list_of_dicts": [
        {"item1": "value1"},
        {"item2": "value2"}
    ]
}

flattened_data = jsonutil.flatten_json(json_data)
print(json.dumps(flattened_data, indent=2))

List of JSON object to CSV file

from mdpython.datautils import jsonutil

out_fl = r"C:\Users\Dell\Onedrive\Desktop\out.csv"

json_data = [
    {
        "name": "John",
        "age": 30,
        "car": {
            "make": "Toyota",
            "model": "Camry"
        },
        "colors": ["red", "blue", "green"]
    }, {
        "name": "Sheema",
        "age": 25,
        "car": {
            "make": "Audi",
            "model": "a4",
            "dimension": [5000, 1850, 1433]
        },
        "colors": ["blue", "yellow"]
    }, {
        "name": "Bruce",
        "car": {
            "make": "Ford"
        }
    }
]

jsonutil.list_to_csv(json_data, out_fl)

Extract URLs from excel file

import mdpython.fileutils.excel as mdexcel
import json
from mdpython.datautils import jsonutil

# Get URLs
xl = mdexcel.Excel(r"c:\users\dell\onedrive\desktop\dummy_data.xlsx")
urls = xl.extract_urls(["A", "B"])
print(json.dumps(urls['data'], indent=2))

# Save as CSV
jsonutil.list_to_csv(urls['data'], r"c:\users\dell\onedrive\desktop\out.csv",
                     colkey=urls['keys'])

Search for text inside JSON data

from mdpython.datautils import jsonutil

json_data = {
    "data": [
        {
            "name": "John",
            "age": 30,
            "car": {
                "make": "Toyota",
                "model": "Camry"
            },
            "colors": ["red", "blue", "green"]
        }, {
            "name": "Sheema",
            "age": 25,
            "car": {
                "make": "Audi",
                "model": "a4",
                "dimension": [5000, 1850, 1433]
            },
            "colors": ["blue", "yellow"]
        }, {
            "name": "Bruce",
            "car": {
                "make": "Ford"
            }
        }
    ]
}

print(jsonutil.search(json_data, "blue"))

# Output
[['data.0.colors.1', 'blue'], ['data.1.colors.0', 'blue']]

Get all objects for a particular key in JSON

from mdpython.datautils import jsonutil

json_data = {
    "data": [
        {
            "name": "John",
            "age": 30,
            "car": {
                "make": "Toyota",
                "model": "Camry"
            },
            "colors": ["red", "blue", "green"]
        }, {
            "name": "Sheema",
            "age": 25,
            "car": {
                "make": "Audi",
                "model": "a4",
                "dimension": [5000, 1850, 1433]
            },
            "colors": ["blue", "yellow"]
        }, {
            "name": "Bruce",
            "car": {
                "make": "Ford"
            }
        }
    ]
}

print(jsonutil.find_values_by_key(json_data, "colors"))

# Output
[['red', 'blue', 'green'], ['blue', 'yellow']]

Reconcile bills and payments

import pandas as pd
from mdpython.account import reconcile

inp_fl = r"C:\Users\Dell\Onedrive\Desktop\input.xlsx"
out_fl = r"C:\Users\Dell\Onedrive\Desktop\output.xlsx"

disc_ar = [2, 2.5, 5, 10]

bill_df = pd.read_excel(inp_fl, usecols="B:C").dropna()
pymt_df = pd.read_excel(inp_fl, usecols="G:H").dropna()

recon = reconcile.reconcile_payment(
    bill_df=bill_df
    , pymt_df=pymt_df
    , bill_dt_col="Bill Date"
    , bill_amt_col="Bill Amount"
    , pymt_dt_col="Payment Date"
    , pymt_amt_col="Payment Amount"
    , disc_ar=disc_ar
)

print(recon.bill_dtl_df)
print(recon.pymt_dtl_df)

recon.to_excel(out_fl)