exploration of datasets

.gitignore

@@ -1,2 +1,2 @@
 venv/
-dataset.py
+notebook.ipynb

app.py

@@ -1,26 +1,29 @@
 import streamlit as st
 import pandas as pd
-import kagglehub
-import zipfile
-import os
+
 
 st.title('Dashboard de Venture Capital')
 st.markdown('Demo portafolio de Machine Learning y Venture Capital')
 
-# Download latest version
-path = kagglehub.dataset_download("sashakorovkina/4808-techstars-backed-companies-in-2024", path="./datasets/")
+# Load CSV into a DataFrame
+data = "./datasets/companies.csv"
+data = pd.read_csv(data)
+
+df = pd.DataFrame(data)
 
-# # Unzip the dataset (if compressed)
-# with zipfile.ZipFile(path, 'r') as zip_ref:
-#     zip_ref.extractall("./datasets")
+# Get the column names for segmented control (e.g., 'Status' column)
+filters = df.columns.tolist()  # This will give a list of column names in the dataframe
 
-# Load CSV into a DataFrame
-csv_path = "./datasets/sashakorovkina/4808-techstars-backed-companies-in-2024.csv"
-df = pd.read_csv(csv_path)
+# Add the segmented control widget to let the user choose a filter
+selected_filter = st.sidebar.segmented_control("Select a column to filter", filters)
 
-# Display DataFrame in Streamlit
-st.write(df.head())
+# Based on the selected filter, display options for filtering
+if selected_filter:
+    unique_values = df[selected_filter].unique().tolist()
+    selected_value = st.sidebar.selectbox(f"Select value to filter by {selected_filter}", unique_values)
 
+    # Filter the dataframe based on the selected value
+    filtered_df = df[df[selected_filter] == selected_value]
 
-# Sidebar and Filter
-st.sidebar.write("Opciones para Filtro")
+    # Display the filtered dataframe
+    st.write(filtered_df)

requirements.txt

@@ -1,2 +1 @@
-streamlit
-kagglehub
+streamlit