File size: 7,292 Bytes
912ec24 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 |
#!/usr/bin/env python3
import os
import re
import glob
import streamlit as st
import streamlit.components.v1 as components
from transformers import pipeline
from urllib.parse import quote
from datetime import datetime
import pytz
import base64
import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
st.set_page_config(page_title="AI Knowledge Tree Builder 📈🌿", page_icon="🌳✨", layout="wide")
trees = {
"Biology": """
0. Biology Core Rules and Future Exceptions
1. Central Dogma DNA RNA Protein
- Current CRISPR RNA editing 🧪
- Research Gene therapy siRNA 🔬
- Future Programmable genetics 🚀
""",
"AI Topics": """
1. Major AI Industry Players 🌐
1. Research Leaders 🎯
- OpenAI: GPT-4 DALL-E Foundation Models 🔵
"""
}
def parse_outline_to_mermaid(outline_text):
lines = outline_text.strip().split('\n')
nodes, edges, clicks, stack = [], [], [], []
for line in lines:
indent = len(line) - len(line.lstrip())
level = indent // 4
label = re.sub(r'^[#*\->\d\.\s]+', '', line.strip())
if label:
node_id = f"N{len(nodes)}"
nodes.append(f'{node_id}["{label}"]')
clicks.append(f'click {node_id} "?q={quote(label)}" _blank')
if stack:
parent_level = stack[-1][0]
if level > parent_level:
edges.append(f"{stack[-1][1]} --> {node_id}")
stack.append((level, node_id))
else:
while stack and stack[-1][0] >= level:
stack.pop()
if stack:
edges.append(f"{stack[-1][1]} --> {node_id}")
stack.append((level, node_id))
else:
stack.append((level, node_id))
return "%%{init: {'themeVariables': {'fontSize': '18px'}}}%%\nflowchart LR\n" + "\n".join(nodes + edges + clicks)
def generate_mermaid_html(mermaid_code):
return f"""
<html><head><script src="https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js"></script>
<style>.centered-mermaid{{display:flex;justify-content:center;margin:20px auto;}}</style></head>
<body><div class="mermaid centered-mermaid">{mermaid_code}</div>
<script>mermaid.initialize({{startOnLoad:true}});</script></body></html>
"""
def grow_tree(base_tree, new_node_name, parent_node):
lines = base_tree.strip().split('\n')
new_lines = []
added = False
for line in lines:
new_lines.append(line)
if parent_node in line and not added:
indent = len(line) - len(line.lstrip())
new_lines.append(f"{' ' * (indent + 4)}- {new_node_name} 🌱")
added = True
return "\n".join(new_lines)
def get_download_link(file_path, mime_type="text/plain"):
with open(file_path, 'rb') as f:
data = f.read()
b64 = base64.b64encode(data).decode()
return f'<a href="data:{mime_type};base64,{b64}" download="{file_path}">Download {file_path}</a>'
@st.cache_resource
def load_generator():
return pipeline("text-generation", model="distilgpt2")
# Main App
st.title("🌳 AI Knowledge Tree Builder 🌱")
if 'current_tree' not in st.session_state:
if os.path.exists("current_tree.md"):
with open("current_tree.md", "r") as f:
st.session_state['current_tree'] = f.read()
else:
st.session_state['current_tree'] = trees["Biology"]
selected_tree = st.selectbox("Select Knowledge Tree", list(trees.keys()))
if selected_tree != st.session_state.get('selected_tree_name', 'Biology'):
st.session_state['current_tree'] = trees[selected_tree]
st.session_state['selected_tree_name'] = selected_tree
with open("current_tree.md", "w") as f:
f.write(st.session_state['current_tree'])
new_node = st.text_input("Add New Node")
parent_node = st.text_input("Parent Node")
if st.button("Grow Tree 🌱") and new_node and parent_node:
st.session_state['current_tree'] = grow_tree(st.session_state['current_tree'], new_node, parent_node)
with open("current_tree.md", "w") as f:
f.write(st.session_state['current_tree'])
st.success(f"Added '{new_node}' under '{parent_node}'!")
st.markdown("### Knowledge Tree Visualization")
mermaid_code = parse_outline_to_mermaid(st.session_state['current_tree'])
components.html(generate_mermaid_html(mermaid_code), height=600)
if st.button("Export Tree as Markdown"):
export_md = f"# Knowledge Tree\n\n## Outline\n{st.session_state['current_tree']}\n\n## Mermaid Diagram\n```mermaid\n{mermaid_code}\n```"
with open("knowledge_tree.md", "w") as f:
f.write(export_md)
st.markdown(get_download_link("knowledge_tree.md", "text/markdown"), unsafe_allow_html=True)
st.subheader("Build ML Model from CSV")
uploaded_file = st.file_uploader("Upload CSV", type="csv")
if uploaded_file:
df = pd.read_csv(uploaded_file)
st.write("Columns:", df.columns.tolist())
feature_cols = st.multiselect("Select feature columns", df.columns)
target_col = st.selectbox("Select target column", df.columns)
if st.button("Train Model"):
X = df[feature_cols].values
y = df[target_col].values
X_tensor = torch.tensor(X, dtype=torch.float32)
y_tensor = torch.tensor(y, dtype=torch.float32).view(-1, 1)
dataset = TensorDataset(X_tensor, y_tensor)
loader = DataLoader(dataset, batch_size=32, shuffle=True)
model = nn.Linear(X.shape[1], 1)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.01)
for epoch in range(10):
for batch_X, batch_y in loader:
optimizer.zero_grad()
outputs = model(batch_X)
loss = criterion(outputs, batch_y)
loss.backward()
optimizer.step()
torch.save(model.state_dict(), "model.pth")
app_code = f"""
import streamlit as st
import torch
import torch.nn as nn
model = nn.Linear({len(feature_cols)}, 1)
model.load_state_dict(torch.load("model.pth"))
model.eval()
st.title("ML Model Demo")
inputs = []
for col in {feature_cols}:
inputs.append(st.number_input(col))
if st.button("Predict"):
input_tensor = torch.tensor([inputs], dtype=torch.float32)
prediction = model(input_tensor).item()
st.write(f"Predicted {target_col}: {{prediction}}")
"""
with open("app.py", "w") as f:
f.write(app_code)
reqs = "streamlit\ntorch\npandas\n"
with open("requirements.txt", "w") as f:
f.write(reqs)
readme = """
# ML Model Demo
## How to run
1. Install requirements: `pip install -r requirements.txt`
2. Run the app: `streamlit run app.py`
3. Input feature values and click "Predict".
"""
with open("README.md", "w") as f:
f.write(readme)
st.markdown(get_download_link("model.pth", "application/octet-stream"), unsafe_allow_html=True)
st.markdown(get_download_link("app.py", "text/plain"), unsafe_allow_html=True)
st.markdown(get_download_link("requirements.txt", "text/plain"), unsafe_allow_html=True)
st.markdown(get_download_link("README.md", "text/markdown"), unsafe_allow_html=True) |