main.py

from preswald import connect, get_df, table, text, plotly
import pandas as pd
import plotly.express as px

# Connect to Preswald
connect()

# Load dataset
df = get_df("Indian_startups_funding")

# Clean column names
df.columns = df.columns.str.strip().str.replace(' ', '_').str.replace(r'[^\w\s]', '', regex=True)

# Convert data types
df['amount'] = pd.to_numeric(df['amount'], errors='coerce')
df['year'] = pd.to_numeric(df['year'], errors='coerce')
df = df.dropna(subset=['amount', 'year'])

# Filter settings
filter_start_year = 2015
filter_end_year = 2021
filter_industry = None  # Example: 'Technology' or None for all industries

# Filter data
filtered = df[(df['year'] >= filter_start_year) & (df['year'] <= filter_end_year)]
if filter_industry:
    filtered = filtered[filtered['vertical'] == filter_industry]

# Display header
text("# InnoFund Insights - Startup Funding Dashboard")
text(f"Data from {filter_start_year} to {filter_end_year}" +
     (f", Industry: {filter_industry}" if filter_industry else ", All Industries"))

# Sample data
table(filtered.head(10))

# High funding startups
high_funding = filtered[filtered['amount'] > 100]
text("## Startups with Over $100M Funding")
table(high_funding[['startup', 'vertical', 'amount', 'year']])

# Top industries by funding
industry_funding = (filtered.groupby('vertical')['amount']
                    .sum()
                    .sort_values(ascending=False)
                    .reset_index()
                    .head(10))
fig1 = px.bar(industry_funding, x='vertical', y='amount',
              title='Top 10 Industries by Total Funding',
              labels={'vertical': 'Industry', 'amount': 'Total Funding (USD)'},
              color='amount', color_continuous_scale='Blues')
plotly(fig1)

# Funding over years
funding_by_year = filtered.groupby('year')['amount'].sum().reset_index()
fig2 = px.line(funding_by_year, x='year', y='amount',
               title='Funding Over the Years',
               labels={'year': 'Year', 'amount': 'Total Funding (USD)'},
               markers=True)
plotly(fig2)