Spaces:
Running
Running
File size: 3,849 Bytes
a165958 45a7450 9349152 a165958 45a7450 a165958 45a7450 a165958 45a7450 99eb020 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 99eb020 45a7450 f88e0fe 45a7450 a165958 45a7450 a165958 45a7450 a165958 45a7450 9349152 45a7450 a165958 45a7450 a165958 45a7450 a165958 3f85ee3 45a7450 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import pandas as pd
import networkx as nx
import matplotlib.pyplot as plt
from io import BytesIO
from PIL import Image
import gradio as gr
# Load and preprocess the dataset
file_path = "cbinsights_data.csv" # Replace with your file path
data = pd.read_csv(file_path)
# Rename columns based on the first row and drop the header row
data.columns = data.iloc[0]
data = data[1:]
data.columns = ["Company", "Valuation_Billions", "Date_Joined", "Country", "City", "Industry", "Select_Investors"]
# Clean and prepare data
data["Valuation_Billions"] = data["Valuation_Billions"].str.replace('$', '').str.split('.').str[0]
data["Valuation_Billions"] = pd.to_numeric(data["Valuation_Billions"], errors='coerce')
data = data.applymap(lambda x: x.strip() if isinstance(x, str) else x)
# Parse the "Select_Investors" column to map investors to companies
investor_company_mapping = {}
for _, row in data.iterrows():
company = row["Company"]
investors = row["Select_Investors"]
if pd.notnull(investors):
for investor in investors.split(","):
investor = investor.strip()
if investor not in investor_company_mapping:
investor_company_mapping[investor] = []
investor_company_mapping[investor].append(company)
# Gradio app function
def generate_graph(selected_investors):
if not selected_investors:
selected_investors = list(investor_company_mapping.keys())
G = nx.Graph()
# Add edges and nodes based on selected investors
for investor in selected_investors:
companies = investor_company_mapping.get(investor, [])
for company in companies:
G.add_edge(investor, company)
# Node sizes based on valuation
node_sizes = []
for node in G.nodes:
if node in investor_company_mapping: # Fixed size for investors
node_sizes.append(2000)
else: # Company size based on valuation
valuation = data.loc[data["Company"] == node, "Valuation_Billions"].values
node_sizes.append(valuation[0] * 100 if len(valuation) > 0 else 100)
# Node colors
node_colors = []
for node in G.nodes:
if node in investor_company_mapping:
node_colors.append("#FF5733") # Distinct color for investors
else:
node_colors.append("#33FF57") # Distinct color for companies
# Create the graph plot
plt.figure(figsize=(18, 18))
pos = nx.spring_layout(G, k=0.2, seed=42) # Fixed seed for consistent layout
nx.draw(
G, pos,
with_labels=True,
node_size=node_sizes,
node_color=node_colors,
font_size=10,
font_weight="bold",
edge_color="gray",
width=1.5
)
plt.title("Venture Funded Companies Visualization", fontsize=20)
plt.axis('off')
# Save plot to BytesIO object
buf = BytesIO()
plt.savefig(buf, format="png", bbox_inches="tight")
plt.close()
buf.seek(0)
# Convert BytesIO to PIL image
image = Image.open(buf)
return image
# Gradio Interface
def main():
investor_list = sorted(investor_company_mapping.keys())
iface = gr.Interface(
fn=generate_graph,
inputs=gr.CheckboxGroup(
choices=investor_list,
label="Select Investors",
value=investor_list # Default to all selected
),
outputs=gr.Image(type="pil", label="Venture Network Graph"),
title="Venture Networks Visualization",
description=(
"Select investors to visualize their investments in various companies. "
"The graph shows connections between investors and the companies they've invested in. "
"Node sizes represent company valuations."
),
flagging_mode="never"
)
iface.launch()
if __name__ == "__main__":
main()
|