reservoirinvest

# needed for Jupyter notebooks
import os
from pathlib import Path
if Path.cwd().parts[-1] == 'notebooks':
    root = Path.cwd().parent
else:
    root = Path.cwd()
os.chdir(root)

reservoirinvest

# Using tasks on create_task for better control of errors
# Ref: [EdgeDB](https://youtu.be/-CzqsgaXUM8?t=2279)


import asyncio
import time
from typing import Callable, Coroutine
import httpx

# Let us start by making a progress reporting async function.

reservoirinvest

########################################################
####  Scrape a table with an known index into pandas
########################################################

import pandas as pd

## Scrape a single table from an URL with table index
symlotmarginurl = "https://www.5paisa.com/5pit/spma.asp"
symlotmargin = pd.read_html(symlotmarginurl)[1]          # It's the second table

reservoirinvest

# replace all values of a pandas column
df['Column Name'].replace('replacement', inplace=True)

# change a column value based on some other column values
df.loc[(df['column1'] == some_value) & (df['column2'] == some_other_value), ['column_to_change']] = new_value

# List unique values in a DataFrame column
df['Column Name'].unique()

# Convert Series datatype to numeric, changing non-numeric values to NaN

reservoirinvest

df = df.rename(columns={'oldName1': 'newName1', 'oldName2': 'newName2'})
# OR
df.rename(columns={'oldName1': 'newName1', 'oldName2': 'newName2'}, inplace=True)

reservoirinvest

df = df.drop('column_name', 1)
# where 1 is the axis number (0 for rows and 1 for columns.)

# To delete the column without having to reassign df you can do:
df.drop('column_name', axis=1, inplace=True)

# To drop a list of columns
columns = ['Col1', 'Col2', ...]
df.drop(columns, inplace=True, axis=1)

reservoirinvest

# for scalar values
df.loc[df['column_name'] == some_value]

# for rows whose column value is in an iterable
df.loc[df['column_name'].isin(some_values)]

# Combine multiple conditions with &:
df.loc[(df['column_name'] == some_value) & df['other_column'].isin(some_values)]

# To select rows whose column value does not equal some_value, use !=: