Spaces:
Runtime error
Runtime error
import time # to simulate a real time data, time loop | |
import numpy as np # np mean, np random | |
import pandas as pd # read csv, df manipulation | |
import plotly.express as px # interactive charts | |
import streamlit as st # π data web app development | |
# PersistDataset ----- | |
import os | |
import csv | |
import gradio as gr | |
from gradio import inputs, outputs | |
import huggingface_hub | |
from huggingface_hub import Repository, hf_hub_download, upload_file | |
from datetime import datetime | |
# Dataset and Token links - change awacke1 to your own HF id, and add a HF_TOKEN copy to your repo for write permissions | |
# This should allow you to save your results to your own Dataset hosted on HF. --- | |
#DATASET_REPO_URL = "https://huggingface.co/datasets/awacke1/Carddata.csv" | |
DATASET_REPO_URL = "https://huggingface.co/datasets/" + "awacke1/PrivateASRWithMemory.csv" | |
#DATASET_REPO_ID = "awacke1/Carddata.csv" | |
DATASET_REPO_ID = "awacke1/PrivateASRWithMemory.csv" | |
DATA_FILENAME = "PrivateASRWithMemory.csv" | |
DATA_FILE = os.path.join("data", DATA_FILENAME) | |
HF_TOKEN = os.environ.get("HF_TOKEN") | |
DataText = "" | |
# --------------------------------------------- | |
SCRIPT = """ | |
<script> | |
if (!window.hasBeenRun) { | |
window.hasBeenRun = true; | |
console.log("should only happen once"); | |
document.querySelector("button.submit").click(); | |
} | |
</script> | |
""" | |
def get_database_session(url): | |
# Create a database session object that points to the URL. | |
return session | |
#Clear memo | |
#Clear all in-memory and on-disk memo caches. | |
def fetch_and_clean_data(url): | |
# Fetch data from URL here, and then clean it up. | |
return data | |
if st.checkbox("Clear All"): | |
# Clear values from *all* memoized functions | |
st.experimental_memo.clear() | |
try: | |
hf_hub_download( | |
repo_id=DATASET_REPO_ID, | |
filename=DATA_FILENAME, | |
cache_dir=DATA_DIRNAME, | |
force_filename=DATA_FILENAME | |
) | |
except: | |
print("file not found") | |
repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL,use_auth_token=HF_TOKEN) | |
# return session | |
print(repo) | |
DataText = repo | |
st.markdown(DataText) | |
def generate_html() -> str: | |
with open(DATA_FILE) as csvfile: | |
reader = csv.DictReader(csvfile) | |
rows = [] | |
for row in reader: | |
rows.append(row) | |
rows.reverse() | |
if len(rows) == 0: | |
return "no messages yet" | |
else: | |
html = "<div class='chatbot'>" | |
for row in rows: | |
html += "<div>" | |
html += f"<span>{row['inputs']}</span>" | |
html += f"<span class='outputs'>{row['outputs']}</span>" | |
html += "</div>" | |
html += "</div>" | |
return html | |
def store_message(name: str, message: str): | |
if name and message: | |
with open(DATA_FILE, "a") as csvfile: | |
writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"]) | |
writer.writerow( | |
{"name": name.strip(), "message": message.strip(), "time": str(datetime.now())} | |
) | |
# uncomment line below to begin saving - | |
commit_url = repo.push_to_hub() | |
return "" | |
#st.set_page_config( | |
# page_title="Real-Time Data Science Dashboard", | |
# page_icon="β ", | |
# layout="wide", | |
#) | |
# read csv from a github repo | |
dataset_url = "https://raw.githubusercontent.com/Lexie88rus/bank-marketing-analysis/master/bank.csv" | |
# read csv from a URL | |
def get_data() -> pd.DataFrame: | |
return pd.read_csv(dataset_url) | |
df = get_data() | |
# dashboard title | |
st.title("Real-Time / Live Data Science Dashboard") | |
# top-level filters | |
job_filter = st.selectbox("Select the Job", pd.unique(df["job"])) | |
# creating a single-element container | |
placeholder = st.empty() | |
# dataframe filter | |
df = df[df["job"] == job_filter] | |
# near real-time / live feed simulation | |
for seconds in range(200): | |
df["age_new"] = df["age"] * np.random.choice(range(1, 5)) | |
df["balance_new"] = df["balance"] * np.random.choice(range(1, 5)) | |
# creating KPIs | |
avg_age = np.mean(df["age_new"]) | |
count_married = int( | |
df[(df["marital"] == "married")]["marital"].count() | |
+ np.random.choice(range(1, 30)) | |
) | |
balance = np.mean(df["balance_new"]) | |
with placeholder.container(): | |
# create three columns | |
kpi1, kpi2, kpi3 = st.columns(3) | |
# fill in those three columns with respective metrics or KPIs | |
kpi1.metric( | |
label="Age β³", | |
value=round(avg_age), | |
delta=round(avg_age) - 10, | |
) | |
kpi2.metric( | |
label="Married Count π", | |
value=int(count_married), | |
delta=-10 + count_married, | |
) | |
kpi3.metric( | |
label="A/C Balance οΌ", | |
value=f"$ {round(balance,2)} ", | |
delta=-round(balance / count_married) * 100, | |
) | |
# create two columns for charts | |
fig_col1, fig_col2 = st.columns(2) | |
with fig_col1: | |
st.markdown("### First Chart") | |
fig = px.density_heatmap( | |
data_frame=df, y="age_new", x="marital" | |
) | |
st.write(fig) | |
with fig_col2: | |
st.markdown("### Second Chart") | |
fig2 = px.histogram(data_frame=df, x="age_new") | |
st.write(fig2) | |
st.markdown("### Detailed Data View") | |
st.dataframe(df) | |
time.sleep(1) |