Create Simple EDA.py
Browse files- pages/Simple EDA.py +33 -0
pages/Simple EDA.py
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
|
| 4 |
+
# EDA and Feature Engineering Page
|
| 5 |
+
st.title("Simple EDA")
|
| 6 |
+
st.markdown("""
|
| 7 |
+
|
| 8 |
+
By performing simple Exploratory Data Analysis (EDA), we can examine the data, identify patterns, and detect anomalies or inconsistencies. This process allows us to clean and preprocess the dataset effectively, ensuring it is well-structured and ready for further analysis or modeling..
|
| 9 |
+
""")
|
| 10 |
+
|
| 11 |
+
# File uploader for dataset
|
| 12 |
+
uploaded_file = st.file_uploader("Upload your dataset (CSV format):", type=["csv"])
|
| 13 |
+
|
| 14 |
+
if uploaded_file is not None:
|
| 15 |
+
# Read and display the dataset
|
| 16 |
+
data = pd.read_csv(uploaded_file)
|
| 17 |
+
st.write("### Uploaded Dataset:")
|
| 18 |
+
st.dataframe(data)
|
| 19 |
+
|
| 20 |
+
# Overview of the dataset
|
| 21 |
+
st.write("### Dataset Overview:")
|
| 22 |
+
st.write(data.describe())
|
| 23 |
+
|
| 24 |
+
# Missing values in the dataset
|
| 25 |
+
st.write("### Missing Values:")
|
| 26 |
+
st.write(data.isnull().sum())
|
| 27 |
+
|
| 28 |
+
# Correlation matrix
|
| 29 |
+
st.write("### Correlation Matrix:")
|
| 30 |
+
st.write(data.corr())
|
| 31 |
+
|
| 32 |
+
else:
|
| 33 |
+
st.warning("Please upload a dataset to proceed with EDA.")
|