You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
miner/frontend/exploration.py

53 lines
1.4 KiB

import pandas as pd
import streamlit as st
import codecs
st.set_page_config(
page_title="Project Miner",
layout="wide"
)
st.title("Home")
### Exploration
uploaded_file = st.file_uploader("Upload your CSV file", type=["csv", "tsv"])
separator = st.selectbox("Separator", [",", ";", "\\t"])
separator = codecs.getdecoder("unicode_escape")(separator)[0]
has_header = st.checkbox("Has header", value=True)
if uploaded_file is not None:
st.session_state.data = pd.read_csv(uploaded_file, sep=separator, header=0 if has_header else 1)
st.session_state.original_data = st.session_state.data
st.success("File loaded successfully!")
if "data" in st.session_state:
data = st.session_state.data
st.write(data.head(10))
st.write(data.tail(10))
st.header("Data Preview")
st.subheader("First 5 Rows")
st.write(data.head())
st.subheader("Last 5 Rows")
st.write(data.tail())
st.header("Data Summary")
st.subheader("Basic Information")
col1, col2 = st.columns(2)
col1.metric("Number of Rows", data.shape[0])
col2.metric("Number of Columns", data.shape[1])
st.write(f"Column Names: {list(data.columns)}")
st.subheader("Missing Values by Column")
missing_values = data.isnull().sum()
st.write(missing_values)
st.subheader("Statistical Summary")
st.write(data.describe())