asehmi

# ISSUE: Stylistically, I prefer to have a top-level controller and then
# form "views" which get laid out on the page in the order they were called.
# With just two forms, though, callback chaining is manageable and won’t result in a tangle,
# but the layout order is inverted, and in this callbacks solution the profile report and forms
# disappear when `cluster_duplicates` is finally called.
#
# (See this thread: https://discuss.streamlit.io/t/selectbox-bug-on-chaining-forms/19927)
#
# For a better solution see: multiform_chaining.py

asehmi

import streamlit as st
from streamlit_pandas_profiling import st_profile_report
from streamlit import session_state as session

import numpy as np
import pandas as pd
from pandas_profiling import ProfileReport

if 'data_uploader_submitted' not in session:
    session.data_uploader_submitted = False

asehmi

# 
# It's a bit of a CSS hack but it is possible to get rid of that
# large amount of whitespace at the top of Streamlit apps!
#
# If this hack stops working, it's likely the Streamlit app CSS
# classes have changed. Open up dev tools and find the new names
# to update the CSS below. :-)
#
# UPDATED 29/4/2022 with new classes
# 

asehmi

# How to use:
#
# [1] Ensure you have `debugpy` installed:
#
#    > pip install debugpy
#
# [2] In your main streamlit app:
#
#    import streamlit_debug
#    streamlit_debug.set(flag=True, wait_for_client=True, host='localhost', port=8765)

asehmi

import streamlit as st
import pandas_profiling
from streamlit_pandas_profiling import st_profile_report
import pandas as pd

st.set_page_config(
    page_title='Data Profiler',
    layout='wide',
    page_icon='🔍'
)

asehmi

### **data.py**

import streamlit as st
import pandas as pd

@st.experimental_memo(persist='disk')
def csv_to_df(excel_file):
    df = pd.read_csv(excel_file)
    return df

asehmi

from datetime import date, datetime
import streamlit as st
import pandas as pd
import mplfinance as mpf
from pandas_datareader import data as pdr

@st.experimental_memo(persist='disk')
def get_historical_data(symbol, start_date = None):
    df = pdr.get_data_yahoo(symbol, start=start_date, end=datetime.now())
    for col in df.columns: