Develop Reference

Streamlit: Display Text after text, not all at once

I want to build a data annotation interface. I read in an excel file, where only a text column is relevant. So "df" could also be replaced by a list of texts. This is my code:
import streamlit as st
import pandas as pd
import numpy as np
st.title('Text Annotation')
df = pd.read_excel('mini_annotation.xlsx')
for i in range(len(df)):
text = df.iloc[i]['Text']
st.write(f"Text {i} out of {len(df)}")
st.write("Please classify the following text:")
st.write("")
st.write(text)
text_list = []
label_list = []
label = st.selectbox("Classification:", ["HOF", "NOT","Not Sure"])
if st.button("Submit"):
text_list.append(text)
label_list.append(label)
df_annotated = pd.DataFrame(columns=['Text', 'Label'])
df_annotated["Text"] = text_list
df_annotated["Label"] = label_list
df_annotated.to_csv("annotated_file.csv", sep=";")
The interface looks like this:
However, I want the interface to display just one text, e.g. the first text of my dataset. After the user has submitted his choice via the "Submit" button, I want the first text to be gone and the second text should be displayed. This process should continue until the last text of the dataset is reached.
How do I do this?
(I am aware of the Error message, for this I just have to add a key to the selectbox, but I am not sure if this is needed in the end)

This task is solved with the help of the session state. U can read about it here: session state
import streamlit as st
import pandas as pd
import numpy as np
st.title('Text Annotation')
df = pd.DataFrame(['Text 1', 'Text 2', 'Text 3', 'Text 4'], columns=['Text'])
if st.session_state.get('count') is None:
st.session_state.count = 0
st.session_state.label_list = []
with st.form("my_form"):
st.write("Progress: ", st.session_state.count, "/", len(df))
if st.session_state.count < len(df):
st.write(df.iloc[st.session_state.count]['Text'])
label = st.selectbox("Classification:", ["HOF", "NOT","Not Sure"])
submitted = st.form_submit_button("Submit")
if submitted:
st.session_state.label_list.append(label)
st.session_state.count += 1
else:
st.write("All done!")
submitted = st.form_submit_button("Submit")
if submitted:
st.write(st.session_state.label_list)

How to sending images to unsaved numbers in pywhatkit?

My aim is to send an image file in whatsapp to various persons who are not on my contact list. Try with pywhatkit. Store the number in an excel sheet and read it by pandas. Loop the number to send the image file. The first number gets the image file successfully, and the remaining numbers WhatsApp will open but the message will not send. Also tell, me how to avoid WhatsApp open in a new tab(chrome)every time.
Here's my code
import pandas as pd
file_name = r'd:\\Recipients data.xlsx'
df = pd.read_excel(file_name)
contact = df['Contact'].tolist()
import pywhatkit
import time
from datetime import datetime
now = datetime.now()
current_time = now.strftime("%H:%M : %S")
h,m,s = current_time.split(':')
print(now)
h1 = int(h)
m1 = int(m)
s1 = int(s)
file_path = r'C:/Users/Asus/Downloads/subadev.jpeg'
for send_number in contact:
new_format = (f'"{str("+91")+str(send_number)}"')
print(new_format)
pywhatkit.sendwhats_image(new_format,file_path)
time.sleep(15)
expecting : send images to every number without open whats app every time

Any way to make my Dash app run faster for a huge amount of data?

I have created a Dash app to read data from a .csv file and represent it, where the user has the option to choose which variable he wants to represent.
The problem I'm facing is that the Dash app keeps freezing or is very slow, most likely due to the amount of sheer data I'm reading (the .csv files I need to read have above 2 million lines).
Is there any way I can make it faster? Maybe optimizing my code in some way?
Any help is appreciated, thanks in advance.
import pandas as pd
import numpy as np
from matplotlib import lines
import plotly.express as px
from dash import Dash, html, dcc,Input, Output
from tkinter import Tk
from tkinter.filedialog import askopenfilename
import webbrowser
print("Checkpoint 1")
def open_file():
global df, drop_list
Tk().withdraw() # we don't want a full GUI, so keep the root window from appearing
filename = askopenfilename() # show an "Open" dialog box and return the path to the selected file
print(filename)
newfilename = filename.replace('/', '\\\\')
print(newfilename)
df = pd.read_csv ('' + newfilename, sep=";", skiprows=4, skipfooter=2, engine='python') # Read csv file using pandas
# Detect all the different signals in the csv
signals = df["Prozesstext"].unique()
signals = pd.DataFrame(signals) # dataframe creation
signals.sort_values(by=0) # after the dataframe is created it can be sorted
drop_list = [] # list used for the dropdown menu
for each in signals[0]:
drop_list.append(each)
app = Dash(__name__)
fig = px.line([]) #figure starts with an empty chart
open_file()
print("Checkpoint 2")
app.layout = html.Div([
html.H1(id = 'H1', children = 'Reading Data from CSV', style = {'textAlign':'center','marginTop':40,'marginBottom':40}),
dcc.Dropdown(drop_list[:-1],id='selection_box'),
html.Div(id='dd-output-container'),
dcc.Graph(
id='trend1',
figure=fig
)
])
webbrowser.open("http://127.0.0.1:8050", new=2, autoraise=True)
# FIRST CALLBACK
#app.callback(
Output(component_id='trend1',component_property='figure'),
Input('selection_box', 'value'),
prevent_initial_call = True
)
def update_trend1(value):
df2 = df[df['Prozesstext'].isin([value])] #without empty spaces it can be just df.column_name
return px.line(df2, x="Zeitstempel", y="Daten", title=value, markers = True) # line chart
if __name__ == '__main__':
app.run_server()
#app.run_server(debug=True)

I suggest the following:
Build a Multi-value dropdown menu with the names of all columns in the CSV file. Look at this here.
Based on the selected columns by a user, the corresponding data will be imported from the CSV file.
It is not clear in your question how you represented the csv data on Dash. I recommend dbc.Table.
By doing this, you will minimize the cost of reading the entire data from the CSV file.

pandas how to get data form google sheet?

The following script generates this error: err:HTTPError: HTTP Error 432: unknown.
Here is my code:
import pandas
googleSheetId = '1iJnkfdDLC_4SHlaWNEbBS0kiJkmE4oEV'
worksheetName = 'Hourly%20Market%20Data'
URL = 'https://docs.google.com/spreadsheets/d/{0}/gviz/tq?tqx=out:csv&sheet={1}'.format(
googleSheetId, worksheetName)
df = pandas.read_csv(URL)
df.head(10)
What is wrong?

Resampling Live Websocket Ticks to Candles using Pandas in python

I am trying to resample live ticks from KiteTicker websocket into OHLC candles using pandas and this is the code I have written, which works fine with single instrument (The commented trd_portfolio on line 9) but doesn't work with multiple instruments (Line 8) as it mixes up data of different instruments.
Is there any way to relate the final candles df to instrument tokens? or make this work with multiple intruments?
I would like to run my algo on multiple instruments at once, please suggest if there is a better way around it.
from kiteconnect import KiteTicker;
from kiteconnect import KiteConnect;
import logging
import time,os,datetime,math;
import winsound
import pandas as pd
trd_portfolio = {954883:"USDINR19MARFUT",4632577:"JUBLFOOD"}
# trd_portfolio = {954883:"USDINR19MARFUT"}
trd_tkn1 = [];
for x in trd_portfolio:
trd_tkn1.append(x)
c_id = '****************'
ak = '************'
asecret = '*************************'
kite = KiteConnect(api_key=ak)
print('[*] Generate access Token : ',kite.login_url())
request_tkn = input('[*] Enter Your Request Token Here : ')[-32:];
data = kite.generate_session(request_tkn, api_secret=asecret)
kite.set_access_token(data['access_token'])
kws = KiteTicker(ak, data['access_token'])
#columns in data frame
df_cols = ["Timestamp", "Token", "LTP"]
data_frame = pd.DataFrame(data=[],columns=df_cols, index=[])
def on_ticks(ws, ticks):
global data_frame, df_cols
data = dict()
for company_data in ticks:
token = company_data["instrument_token"]
ltp = company_data["last_price"]
timestamp = company_data['timestamp']
data[timestamp] = [timestamp, token, ltp]
tick_df = pd.DataFrame(data.values(), columns=df_cols, index=data.keys()) #
data_frame = data_frame.append(tick_df)
ggframe=data_frame.set_index(['Timestamp'],['Token'])
print ggframe
gticks=ggframe.ix[:,['LTP']]
candles=gticks['LTP'].resample('1min').ohlc().dropna()
print candles
def on_connect(kws , response):
print('Connected')
kws.subscribe(trd_tkn1)
kws.set_mode(kws.MODE_FULL, trd_tkn1)
def on_close(ws, code, reason):
print('Connection Error')
kws.on_ticks = on_ticks
kws.on_connect = on_connect
kws.on_close = on_close
kws.connect()

I don't have access to the Kite API, but I've been looking at some code snippets that use it trying to figure out another issue I'm having related to websockets. I came across this open question, and I think I can help, though I can't really test this solution.
The problem I think is that you're not calculating OHLC for each "token"... it just does it for all tokens.
data_frame = data_frame.append(tick_df)
ggframe=data_frame.set_index('Timestamp')
candles=ggframe.groupby('token').resample('1min').agg({'LTP':'ohlc'})
You'll get a multi-index output, but the column names might not quite line up for the rest of your code. To fix that:
candles.columns=['open','high','low','close']