Spaces:
Sleeping
Sleeping
Upload 3 files
Browse files- Dockerfile +12 -0
- requirements.txt +7 -0
- server.py +1585 -0
Dockerfile
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM python:3.11-slim
|
| 2 |
+
|
| 3 |
+
WORKDIR /app
|
| 4 |
+
|
| 5 |
+
COPY requirements.txt requirements.txt
|
| 6 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 7 |
+
|
| 8 |
+
COPY . .
|
| 9 |
+
|
| 10 |
+
EXPOSE 8051
|
| 11 |
+
|
| 12 |
+
CMD ["python", "server.py"]
|
requirements.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dash
|
| 2 |
+
pandas
|
| 3 |
+
plotly
|
| 4 |
+
networkx
|
| 5 |
+
numpy
|
| 6 |
+
pyarrow
|
| 7 |
+
scipy
|
server.py
ADDED
|
@@ -0,0 +1,1585 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import dash
|
| 2 |
+
from dash import dcc, html, Output, Input, State
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import plotly.graph_objs as go
|
| 5 |
+
import plotly.express as px
|
| 6 |
+
import networkx as nx
|
| 7 |
+
import numpy as np
|
| 8 |
+
import os
|
| 9 |
+
import re
|
| 10 |
+
import colorsys
|
| 11 |
+
from functools import lru_cache
|
| 12 |
+
|
| 13 |
+
# === Основные параметры ===
|
| 14 |
+
BASE_PARQUET_DIR = r"/app/parquet"
|
| 15 |
+
PDF_PATH = r"/app/pdf/report.pdf"
|
| 16 |
+
|
| 17 |
+
ORG_ID = 373
|
| 18 |
+
YEAR_START = 2005
|
| 19 |
+
YEAR_END = 2024
|
| 20 |
+
COLOR_ALPHA = 0.8
|
| 21 |
+
COLOR_LIGHTEN = 0.2
|
| 22 |
+
WEB20_PALETTE = [
|
| 23 |
+
"#0074D9", "#00B8D4", "#6A4C93", "#FF851B", "#B10DC9",
|
| 24 |
+
"#FFDC00", "#39CCCC", "#FFB347", "#7FDBFF", "#3D9970",
|
| 25 |
+
"#F012BE", "#85144b", "#FF6F61", "#C70039", "#FF9F1C",
|
| 26 |
+
"#C0CA33", "#2ECC40", "#01FF70", "#FF4136", "#B8E986",
|
| 27 |
+
]
|
| 28 |
+
MAX_LEN_HOVER = 60
|
| 29 |
+
SHOW_SUMMARY_RU = False
|
| 30 |
+
SHOW_SUMMARY_EN = True
|
| 31 |
+
SPRING_K = 0.6
|
| 32 |
+
SPRING_ITER = 500
|
| 33 |
+
NODE_SIZE_BASE = 10
|
| 34 |
+
NODE_SIZE_MAX = 50
|
| 35 |
+
EDGE_ALPHA = 0.13
|
| 36 |
+
EDGE_WIDTH_BASE = 1
|
| 37 |
+
EDGE_WIDTH_MAX = 10
|
| 38 |
+
SINGLE_NODE_BORDER_WIDTH = 1
|
| 39 |
+
NODE_SIZE_SCALE_MODE = "diameter"
|
| 40 |
+
|
| 41 |
+
import threading
|
| 42 |
+
|
| 43 |
+
# Кеш для датафреймов
|
| 44 |
+
_PARQUET_CACHE = {}
|
| 45 |
+
_CACHE_LOCK = threading.Lock()
|
| 46 |
+
|
| 47 |
+
def load_df_cached(name, **kwargs):
|
| 48 |
+
"""Быстрая загрузка parquet-файлов с кешированием в памяти."""
|
| 49 |
+
with _CACHE_LOCK:
|
| 50 |
+
if name not in _PARQUET_CACHE:
|
| 51 |
+
_PARQUET_CACHE[name] = pd.read_parquet(os.path.join(BASE_PARQUET_DIR, name), **kwargs)
|
| 52 |
+
return _PARQUET_CACHE[name]
|
| 53 |
+
|
| 54 |
+
PRELOAD_FILES = [
|
| 55 |
+
fname for fname in os.listdir(BASE_PARQUET_DIR)
|
| 56 |
+
if fname.endswith(".parquet")
|
| 57 |
+
]
|
| 58 |
+
|
| 59 |
+
print("Загрузка файлов в кеш:", PRELOAD_FILES)
|
| 60 |
+
for fname in PRELOAD_FILES:
|
| 61 |
+
load_df_cached(fname)
|
| 62 |
+
print("Все parquet-файлы успешно загружены в RAM.")
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def parquet_path(*parts):
|
| 69 |
+
return os.path.join(BASE_PARQUET_DIR, *parts)
|
| 70 |
+
|
| 71 |
+
def load_df(name, **kwargs):
|
| 72 |
+
return pd.read_parquet(parquet_path(name), **kwargs)
|
| 73 |
+
|
| 74 |
+
def list_period_files(prefix):
|
| 75 |
+
files = []
|
| 76 |
+
for fname in os.listdir(BASE_PARQUET_DIR):
|
| 77 |
+
if fname.startswith(prefix + "__") and fname.endswith(".parquet"):
|
| 78 |
+
period = fname.split("__")[1].replace(".parquet", "")
|
| 79 |
+
files.append((period, fname))
|
| 80 |
+
return sorted(files)
|
| 81 |
+
|
| 82 |
+
def get_periods(prefix):
|
| 83 |
+
files = list_period_files(prefix)
|
| 84 |
+
result = []
|
| 85 |
+
for period, fname in files:
|
| 86 |
+
label = period.replace("_", "–")
|
| 87 |
+
result.append({
|
| 88 |
+
"key": period,
|
| 89 |
+
"label": label,
|
| 90 |
+
"fname": fname
|
| 91 |
+
})
|
| 92 |
+
return result
|
| 93 |
+
|
| 94 |
+
PERIODS = get_periods("bar_data")
|
| 95 |
+
period_options = [{"label": p["label"], "value": p["key"]} for p in PERIODS]
|
| 96 |
+
|
| 97 |
+
# === 0. График продуктивности ===
|
| 98 |
+
def load_and_prepare_data(year_start, year_end, org_id):
|
| 99 |
+
df_orgs = load_df_cached("organizations.parquet")
|
| 100 |
+
df_values = load_df_cached("publication_values.parquet")[["pub_id", "fract_value"]].rename(columns={"fract_value": "fract_author_value"})
|
| 101 |
+
df_orgs = df_orgs[pd.notnull(df_orgs["year"])].copy()
|
| 102 |
+
df_orgs["year"] = df_orgs["year"].astype(int)
|
| 103 |
+
df_orgs_filtered = df_orgs[df_orgs["year"].between(year_start, year_end)].copy()
|
| 104 |
+
df_hse = df_orgs_filtered[df_orgs_filtered["org_id"] == org_id]
|
| 105 |
+
df = df_hse.merge(df_values, on="pub_id", how="left")
|
| 106 |
+
affil_counts = df_orgs_filtered.groupby(["pub_id", "author_id"]).size().reset_index(name="affil_count")
|
| 107 |
+
multi_affil = affil_counts[affil_counts["affil_count"] > 1]["pub_id"].nunique()
|
| 108 |
+
df = df.merge(affil_counts, on=["pub_id", "author_id"], how="left")
|
| 109 |
+
df["fract_author_affiliation_value"] = df["fract_author_value"] / df["affil_count"]
|
| 110 |
+
return df, multi_affil
|
| 111 |
+
|
| 112 |
+
def build_productivity_figure(df, multi_affil):
|
| 113 |
+
pubs_per_year = df.drop_duplicates(subset=["pub_id", "year"]).groupby("year")["pub_id"].count()
|
| 114 |
+
authors_per_year = df.drop_duplicates(subset=["year", "author_id"]).groupby("year")["author_id"].count()
|
| 115 |
+
value_per_year = df.groupby("year")["fract_author_value"].sum()
|
| 116 |
+
adjusted_value_per_year = df.groupby("year")["fract_author_affiliation_value"].sum()
|
| 117 |
+
total_val = value_per_year.sum()
|
| 118 |
+
total_a_val = adjusted_value_per_year.sum()
|
| 119 |
+
total_pubs = df["pub_id"].nunique()
|
| 120 |
+
total_authors = df["author_id"].nunique()
|
| 121 |
+
percent_multi = multi_affil / total_pubs * 100 if total_pubs > 0 else 0
|
| 122 |
+
|
| 123 |
+
fig = go.Figure()
|
| 124 |
+
fig.add_bar(
|
| 125 |
+
x=value_per_year.index,
|
| 126 |
+
y=value_per_year.values,
|
| 127 |
+
marker_color="rgba(0,128,0,0.25)",
|
| 128 |
+
name=f"Продуктивность (без учёта множественных аффилиаций): {total_val:.1f}"
|
| 129 |
+
)
|
| 130 |
+
fig.add_bar(
|
| 131 |
+
x=adjusted_value_per_year.index,
|
| 132 |
+
y=adjusted_value_per_year.values,
|
| 133 |
+
marker_color="rgba(0,128,0,0.6)",
|
| 134 |
+
name=f"Продуктивность (с учётом множественных аффилиаций): {total_a_val:.1f}"
|
| 135 |
+
)
|
| 136 |
+
fig.add_trace(go.Scatter(
|
| 137 |
+
x=pubs_per_year.index, y=pubs_per_year.values,
|
| 138 |
+
name=f"Публикации: {total_pubs}",
|
| 139 |
+
mode='lines+markers',
|
| 140 |
+
line=dict(color="salmon", width=2),
|
| 141 |
+
yaxis="y2"
|
| 142 |
+
))
|
| 143 |
+
fig.add_trace(go.Scatter(
|
| 144 |
+
x=authors_per_year.index, y=authors_per_year.values,
|
| 145 |
+
name=f"Авторы: {total_authors}",
|
| 146 |
+
mode='lines+markers',
|
| 147 |
+
line=dict(color="royalblue", width=2),
|
| 148 |
+
yaxis="y2"
|
| 149 |
+
))
|
| 150 |
+
fig.update_layout(
|
| 151 |
+
xaxis=dict(title="Год", tickmode='linear', tick0=int(value_per_year.index.min()), dtick=1),
|
| 152 |
+
yaxis=dict(title="Продуктивность"),
|
| 153 |
+
yaxis2=dict(
|
| 154 |
+
title="Число публикаций / авторов",
|
| 155 |
+
overlaying='y',
|
| 156 |
+
side='right'
|
| 157 |
+
),
|
| 158 |
+
legend=dict(x=0.01, y=0.99, bgcolor='rgba(255,255,255,0.7)', bordercolor="gray"),
|
| 159 |
+
template="plotly_white",
|
| 160 |
+
margin=dict(l=40, r=40, t=40, b=40),
|
| 161 |
+
height=470,
|
| 162 |
+
autosize=True
|
| 163 |
+
)
|
| 164 |
+
return fig
|
| 165 |
+
|
| 166 |
+
# === Авторы и аннотации
|
| 167 |
+
authors_df = load_df_cached("authors.parquet")
|
| 168 |
+
author_id2short = dict(zip(authors_df["author_id"], authors_df["short_author_name"]))
|
| 169 |
+
pub_content_df = load_df_cached("publication_content.parquet")
|
| 170 |
+
|
| 171 |
+
# === 1. GRNTI/GRNTI_AGG
|
| 172 |
+
def grnti_hex_to_rgba(hex_color, alpha=COLOR_ALPHA):
|
| 173 |
+
hex_color = hex_color.lstrip('#')
|
| 174 |
+
r, g, b = (int(hex_color[i:i+2], 16) for i in (0, 2, 4))
|
| 175 |
+
return f"rgba({r},{g},{b},{alpha})"
|
| 176 |
+
|
| 177 |
+
def grnti_lighten_color(hex_color, factor=COLOR_LIGHTEN):
|
| 178 |
+
hex_color = hex_color.lstrip('#')
|
| 179 |
+
r, g, b = [int(hex_color[i:i+2], 16) for i in (0, 2, 4)]
|
| 180 |
+
r = int(r + (255 - r) * factor)
|
| 181 |
+
g = int(g + (255 - g) * factor)
|
| 182 |
+
b = int(b + (255 - b) * factor)
|
| 183 |
+
return f'#{r:02x}{g:02x}{b:02x}'
|
| 184 |
+
|
| 185 |
+
def grnti_get_lvl1_colors(df, alpha=COLOR_ALPHA, lighten=COLOR_LIGHTEN):
|
| 186 |
+
lvl1_codes = sorted(df['code_lvl1'].dropna().unique())
|
| 187 |
+
palette = WEB20_PALETTE
|
| 188 |
+
if len(lvl1_codes) > len(palette):
|
| 189 |
+
base_len = len(palette)
|
| 190 |
+
palette_extended = []
|
| 191 |
+
for i in range(len(lvl1_codes)):
|
| 192 |
+
base = palette[i % base_len]
|
| 193 |
+
if i < base_len:
|
| 194 |
+
palette_extended.append(base)
|
| 195 |
+
else:
|
| 196 |
+
rgb = tuple(int(base[j:j+2], 16)/255. for j in (1,3,5))
|
| 197 |
+
h, s, v = colorsys.rgb_to_hsv(*rgb)
|
| 198 |
+
v = min(1, v * (0.8 + 0.2 * ((i//base_len)%2)))
|
| 199 |
+
r, g, b = colorsys.hsv_to_rgb(h, s, v)
|
| 200 |
+
palette_extended.append('#%02x%02x%02x' % (int(r*255), int(g*255), int(b*255)))
|
| 201 |
+
palette = palette_extended
|
| 202 |
+
color_map = {
|
| 203 |
+
code: grnti_hex_to_rgba(grnti_lighten_color(palette[i], factor=lighten), alpha=alpha)
|
| 204 |
+
for i, code in enumerate(lvl1_codes)
|
| 205 |
+
}
|
| 206 |
+
return color_map
|
| 207 |
+
|
| 208 |
+
def grnti_make_treemap(df, norm_mode):
|
| 209 |
+
if norm_mode == 'value':
|
| 210 |
+
col = 'value'
|
| 211 |
+
label_percent = "Доля:"
|
| 212 |
+
total = df['value'].sum()
|
| 213 |
+
else:
|
| 214 |
+
if 'npubs' not in df.columns:
|
| 215 |
+
df['npubs'] = df['frac_npubs']
|
| 216 |
+
col = 'npubs'
|
| 217 |
+
label_percent = "Доля публикаций:"
|
| 218 |
+
total = df['npubs'].sum()
|
| 219 |
+
color_map = grnti_get_lvl1_colors(df, alpha=COLOR_ALPHA, lighten=COLOR_LIGHTEN)
|
| 220 |
+
df_lvl1 = df[df['code_lvl2'].isnull()].copy()
|
| 221 |
+
df_lvl2 = df[df['code_lvl2'].notnull()].copy()
|
| 222 |
+
labels, parents, customdata, values_out, marker_colors = [], [], [], [], []
|
| 223 |
+
|
| 224 |
+
for _, row in df_lvl1.iterrows():
|
| 225 |
+
l = f"{row['code_lvl1']} {row['name_lvl1']}"
|
| 226 |
+
labels.append(l)
|
| 227 |
+
parents.append("")
|
| 228 |
+
values_out.append(row[col])
|
| 229 |
+
customdata.append([
|
| 230 |
+
row['code_lvl1'],
|
| 231 |
+
row['name_lvl1'],
|
| 232 |
+
row[col] / total if total else 0,
|
| 233 |
+
])
|
| 234 |
+
marker_colors.append(color_map.get(row['code_lvl1'], "rgba(200,200,200,0.3)"))
|
| 235 |
+
|
| 236 |
+
for _, row in df_lvl2.iterrows():
|
| 237 |
+
l = f"{row['code_lvl2']} {row['name_lvl2']}"
|
| 238 |
+
labels.append(l)
|
| 239 |
+
parents.append(f"{row['code_lvl1']} {row['name_lvl1']}")
|
| 240 |
+
values_out.append(row[col])
|
| 241 |
+
customdata.append([
|
| 242 |
+
row['code_lvl2'],
|
| 243 |
+
row['name_lvl2'],
|
| 244 |
+
row[col] / total if total else 0,
|
| 245 |
+
])
|
| 246 |
+
marker_colors.append(color_map.get(row['code_lvl1'], "rgba(200,200,200,0.3)"))
|
| 247 |
+
|
| 248 |
+
label_seen = {}
|
| 249 |
+
for i, label in enumerate(labels):
|
| 250 |
+
orig_label = label
|
| 251 |
+
idx = 1
|
| 252 |
+
while label in label_seen:
|
| 253 |
+
label = f"{orig_label} [{idx}]"
|
| 254 |
+
idx += 1
|
| 255 |
+
label_seen[label] = 1
|
| 256 |
+
labels[i] = label
|
| 257 |
+
|
| 258 |
+
hovertemplates = []
|
| 259 |
+
for parent, cd in zip(parents, customdata):
|
| 260 |
+
hovertemplates.append(
|
| 261 |
+
f"Код: {cd[0]}<br>Название: {cd[1]}<br>{label_percent} {cd[2]:.1%}<extra></extra>"
|
| 262 |
+
)
|
| 263 |
+
|
| 264 |
+
texttemplate = (
|
| 265 |
+
"Код: %{customdata[0]}<br>"
|
| 266 |
+
"Название: %{customdata[1]}<br>"
|
| 267 |
+
f"{label_percent} "+"%{customdata[2]:.1%}"
|
| 268 |
+
)
|
| 269 |
+
|
| 270 |
+
fig = go.Figure(go.Treemap(
|
| 271 |
+
labels=labels,
|
| 272 |
+
parents=parents,
|
| 273 |
+
values=values_out,
|
| 274 |
+
customdata=customdata,
|
| 275 |
+
marker_colors=marker_colors,
|
| 276 |
+
texttemplate=texttemplate,
|
| 277 |
+
hovertemplate=hovertemplates,
|
| 278 |
+
branchvalues="total"
|
| 279 |
+
))
|
| 280 |
+
fig.update_layout(
|
| 281 |
+
margin=dict(t=20, l=0, r=0, b=0),
|
| 282 |
+
title=None
|
| 283 |
+
)
|
| 284 |
+
return fig
|
| 285 |
+
|
| 286 |
+
@lru_cache(maxsize=12)
|
| 287 |
+
def grnti_load_df_by_period(period_label):
|
| 288 |
+
fname = f"grnti_agg_result_multi__{period_label}.parquet"
|
| 289 |
+
return load_df_cached(fname)
|
| 290 |
+
|
| 291 |
+
# === Кластеры и bar ===
|
| 292 |
+
@lru_cache(maxsize=8)
|
| 293 |
+
def load_cluster_data(period_key):
|
| 294 |
+
info = load_df_cached(f"coauthor_clusters_info__{period_key}.parquet")
|
| 295 |
+
summary = load_df_cached(f"coauthor_clusters_summary__{period_key}.parquet")
|
| 296 |
+
return info, summary
|
| 297 |
+
|
| 298 |
+
@lru_cache(maxsize=8)
|
| 299 |
+
def load_bar_data(period_key):
|
| 300 |
+
return load_df_cached(f"bar_data__{period_key}.parquet")
|
| 301 |
+
|
| 302 |
+
|
| 303 |
+
|
| 304 |
+
def period_label_to_filename(period_label):
|
| 305 |
+
# Преобразуем любые тире и пробелы к подчёркиванию
|
| 306 |
+
# '2005–2024' -> '2005_2024'
|
| 307 |
+
return period_label.replace("–", "_").replace("-", "_").replace(" ", "")
|
| 308 |
+
|
| 309 |
+
@lru_cache(maxsize=8)
|
| 310 |
+
def load_science_map_sheet(period_label):
|
| 311 |
+
fname = period_label_to_filename(period_label)
|
| 312 |
+
parquet_path = os.path.join(BASE_PARQUET_DIR, f"hse_science_map__{fname}.parquet")
|
| 313 |
+
|
| 314 |
+
return pd.read_parquet(parquet_path)
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
|
| 318 |
+
def cluster_sorter(vals):
|
| 319 |
+
numeric = []
|
| 320 |
+
non_numeric = []
|
| 321 |
+
for v in vals:
|
| 322 |
+
try:
|
| 323 |
+
numeric.append(int(v))
|
| 324 |
+
except Exception:
|
| 325 |
+
non_numeric.append(v)
|
| 326 |
+
numeric = [str(x) for x in sorted(numeric)]
|
| 327 |
+
non_numeric = sorted(non_numeric)
|
| 328 |
+
return numeric + non_numeric
|
| 329 |
+
|
| 330 |
+
def get_cluster_labels(metrics_df, clusters_sorted):
|
| 331 |
+
labels = []
|
| 332 |
+
for cid in clusters_sorted:
|
| 333 |
+
authors = metrics_df[metrics_df['cluster_id'] == int(cid)]
|
| 334 |
+
if authors.empty:
|
| 335 |
+
labels.append(f'К{cid}')
|
| 336 |
+
continue
|
| 337 |
+
max_centrality = authors['degree_centrality'].max()
|
| 338 |
+
top_authors = authors[authors['degree_centrality'] == max_centrality]['author_short'].tolist()
|
| 339 |
+
names = ', '.join(top_authors)
|
| 340 |
+
if len(authors) > len(top_authors):
|
| 341 |
+
names += ' и др.'
|
| 342 |
+
labels.append(f"{names} К{cid}")
|
| 343 |
+
return labels
|
| 344 |
+
|
| 345 |
+
def get_hover_texts(metrics_df, clusters_sorted, hse_vals, th_vals, other_vals):
|
| 346 |
+
hover_hse, hover_2th, hover_other = [], [], []
|
| 347 |
+
for idx, cid in enumerate(clusters_sorted):
|
| 348 |
+
authors_df = metrics_df[metrics_df['cluster_id'] == int(cid)].copy()
|
| 349 |
+
authors_df = authors_df.sort_values('total_value', ascending=False)
|
| 350 |
+
hse_value = hse_vals[::-1].iloc[idx]
|
| 351 |
+
th_value = th_vals[::-1].iloc[idx]
|
| 352 |
+
other_value = other_vals[::-1].iloc[idx]
|
| 353 |
+
if authors_df.empty:
|
| 354 |
+
hover_hse.append(f"Продуктивность: {hse_value:.1f}<br>Авторы:<br>Нет авторов")
|
| 355 |
+
else:
|
| 356 |
+
lines = [
|
| 357 |
+
f"{i}. {row.author_short} — {row.total_value:.1f}"
|
| 358 |
+
for i, row in enumerate(authors_df.itertuples(), 1)
|
| 359 |
+
]
|
| 360 |
+
hover_hse.append(
|
| 361 |
+
f"Продуктивность: {hse_value:.1f}<br>Авторы:<br>" + "<br>".join(lines)
|
| 362 |
+
)
|
| 363 |
+
hover_2th.append(f"Продуктивность: {th_value:.1f}")
|
| 364 |
+
hover_other.append(f"Продуктивность: {other_value:.1f}")
|
| 365 |
+
return hover_hse, hover_2th, hover_other
|
| 366 |
+
|
| 367 |
+
def make_figure(df, period_label, sort_by='sum'):
|
| 368 |
+
df = df.copy()
|
| 369 |
+
df['sum_value'] = df['hse_value'] + df['2th_org_value'] + df['other_orgs_value']
|
| 370 |
+
df['hse_plus_2th'] = df['hse_value'] + df['2th_org_value']
|
| 371 |
+
|
| 372 |
+
if sort_by == 'sum':
|
| 373 |
+
df_sorted = df.sort_values("sum_value", ascending=False).reset_index(drop=True)
|
| 374 |
+
elif sort_by == 'hse_plus_2th':
|
| 375 |
+
df_sorted = df.sort_values("hse_plus_2th", ascending=False).reset_index(drop=True)
|
| 376 |
+
elif sort_by == 'hse':
|
| 377 |
+
df_sorted = df.sort_values("hse_value", ascending=False).reset_index(drop=True)
|
| 378 |
+
else:
|
| 379 |
+
raise ValueError('sort_by must be "sum", "hse_plus_2th" or "hse"')
|
| 380 |
+
|
| 381 |
+
clusters_sorted = df_sorted['cluster_id'].tolist()[::-1]
|
| 382 |
+
# --- Метрики для ярлыков и ховеров ---
|
| 383 |
+
metrics_df = load_df_cached(f"coauthor_clusters_metrics__{period_label}.parquet")
|
| 384 |
+
y_labels = get_cluster_labels(metrics_df, clusters_sorted)
|
| 385 |
+
hover_hse, hover_2th, hover_other = get_hover_texts(
|
| 386 |
+
metrics_df, clusters_sorted,
|
| 387 |
+
df_sorted['hse_value'], df_sorted['2th_org_value'], df_sorted['other_orgs_value']
|
| 388 |
+
)
|
| 389 |
+
|
| 390 |
+
sum_values = df_sorted['sum_value']
|
| 391 |
+
hse_text = [
|
| 392 |
+
f"{100 * v / s:.1f}%" if s > 0 else ""
|
| 393 |
+
for v, s in zip(df_sorted['hse_value'][::-1], sum_values[::-1])
|
| 394 |
+
]
|
| 395 |
+
org2_text = [
|
| 396 |
+
f"{100 * v / s:.1f}%" if s > 0 else ""
|
| 397 |
+
for v, s in zip(df_sorted['2th_org_value'][::-1], sum_values[::-1])
|
| 398 |
+
]
|
| 399 |
+
other_text = [
|
| 400 |
+
f"{100 * v / s:.1f}%" if s > 0 else ""
|
| 401 |
+
for v, s in zip(df_sorted['other_orgs_value'][::-1], sum_values[::-1])
|
| 402 |
+
]
|
| 403 |
+
|
| 404 |
+
fig = go.Figure()
|
| 405 |
+
fig.add_trace(go.Bar(
|
| 406 |
+
y=y_labels,
|
| 407 |
+
x=df_sorted['hse_value'][::-1],
|
| 408 |
+
orientation='h',
|
| 409 |
+
name='Ядро организации',
|
| 410 |
+
marker_color='royalblue',
|
| 411 |
+
text=hse_text,
|
| 412 |
+
textposition='inside',
|
| 413 |
+
insidetextanchor='middle',
|
| 414 |
+
hovertext=hover_hse,
|
| 415 |
+
hoverinfo="text"
|
| 416 |
+
))
|
| 417 |
+
fig.add_trace(go.Bar(
|
| 418 |
+
y=y_labels,
|
| 419 |
+
x=df_sorted['2th_org_value'][::-1],
|
| 420 |
+
orientation='h',
|
| 421 |
+
name='Совместители',
|
| 422 |
+
marker_color='orange',
|
| 423 |
+
text=org2_text,
|
| 424 |
+
textposition='inside',
|
| 425 |
+
insidetextanchor='middle',
|
| 426 |
+
hovertext=hover_2th,
|
| 427 |
+
hoverinfo="text"
|
| 428 |
+
))
|
| 429 |
+
fig.add_trace(go.Bar(
|
| 430 |
+
y=y_labels,
|
| 431 |
+
x=df_sorted['other_orgs_value'][::-1],
|
| 432 |
+
orientation='h',
|
| 433 |
+
name='Другие',
|
| 434 |
+
marker_color='lightgray',
|
| 435 |
+
text=other_text,
|
| 436 |
+
textposition='inside',
|
| 437 |
+
insidetextanchor='middle',
|
| 438 |
+
hovertext=hover_other,
|
| 439 |
+
hoverinfo="text"
|
| 440 |
+
))
|
| 441 |
+
fig.update_layout(
|
| 442 |
+
barmode='stack',
|
| 443 |
+
xaxis_title='Общая продуктивность публикаций кластера',
|
| 444 |
+
yaxis_title='Кластер',
|
| 445 |
+
height=max(600, 30*len(df_sorted)),
|
| 446 |
+
legend_title_text='',
|
| 447 |
+
template='simple_white',
|
| 448 |
+
xaxis=dict(side='top'),
|
| 449 |
+
legend=dict(
|
| 450 |
+
orientation="h",
|
| 451 |
+
x=0,
|
| 452 |
+
y=1.02,
|
| 453 |
+
xanchor='left',
|
| 454 |
+
yanchor='bottom'
|
| 455 |
+
)
|
| 456 |
+
)
|
| 457 |
+
return fig
|
| 458 |
+
|
| 459 |
+
# === Сеть соавторства (network graph)
|
| 460 |
+
def plotly_network_graph(
|
| 461 |
+
df, df_summary,
|
| 462 |
+
weight_mode="value",
|
| 463 |
+
show_singles=True,
|
| 464 |
+
node_size_scale_mode=NODE_SIZE_SCALE_MODE,
|
| 465 |
+
k=SPRING_K, iterations=SPRING_ITER
|
| 466 |
+
):
|
| 467 |
+
import networkx as nx
|
| 468 |
+
G = nx.Graph()
|
| 469 |
+
for _, row in df.iterrows():
|
| 470 |
+
if not G.has_node(row['author_id']):
|
| 471 |
+
G.add_node(row['author_id'], cluster=row['cluster_id'])
|
| 472 |
+
pubs = df.groupby('pub_id')
|
| 473 |
+
edge_weights = {}
|
| 474 |
+
for pub_id, group in pubs:
|
| 475 |
+
authors = group['author_id'].tolist()
|
| 476 |
+
pub_value = group['fract_author_affiliation_value'].sum() if 'fract_author_affiliation_value' in group else 1
|
| 477 |
+
for i in range(len(authors)):
|
| 478 |
+
for j in range(i+1, len(authors)):
|
| 479 |
+
edge = tuple(sorted((authors[i], authors[j])))
|
| 480 |
+
if edge not in edge_weights:
|
| 481 |
+
edge_weights[edge] = {"count": 0, "value": 0.0}
|
| 482 |
+
edge_weights[edge]["count"] += 1
|
| 483 |
+
edge_weights[edge]["value"] += pub_value
|
| 484 |
+
for (a, b), ew in edge_weights.items():
|
| 485 |
+
G.add_edge(a, b, count=ew["count"], value=ew["value"])
|
| 486 |
+
|
| 487 |
+
if G.number_of_nodes() == 0 or G.number_of_edges() == 0:
|
| 488 |
+
return go.Figure(layout=go.Layout(
|
| 489 |
+
title="Нет кластеров для отображения",
|
| 490 |
+
margin=dict(t=60, b=30, l=10, r=10),
|
| 491 |
+
template="plotly_white"
|
| 492 |
+
))
|
| 493 |
+
|
| 494 |
+
pos = nx.spring_layout(G, k=k, iterations=iterations, seed=42)
|
| 495 |
+
|
| 496 |
+
nice_colors = [
|
| 497 |
+
"#E53935", "#1E88E5", "#43A047", "#FDD835", "#8E24AA",
|
| 498 |
+
"#00ACC1", "#F4511E", "#3949AB", "#7CB342", "#FB8C00",
|
| 499 |
+
"#C2185B", "#00897B", "#C0CA33", "#5E35B1", "#039BE5",
|
| 500 |
+
"#E64A19", "#9E9D24", "#6D4C41", "#546E7A", "#D81B60",
|
| 501 |
+
"#F06292", "#7E57C2", "#26A69A", "#789262", "#FDD835",
|
| 502 |
+
]
|
| 503 |
+
cluster_ids_sorted = sorted(df_summary["cluster_id"].unique())
|
| 504 |
+
palette = nice_colors * ((len(cluster_ids_sorted)//len(nice_colors))+2)
|
| 505 |
+
cluster_color_map = {
|
| 506 |
+
cluster: palette[i % len(palette)] for i, cluster in enumerate(cluster_ids_sorted)
|
| 507 |
+
}
|
| 508 |
+
|
| 509 |
+
is_single_dict = {}
|
| 510 |
+
if 'is_single' in df_summary.columns:
|
| 511 |
+
is_single_dict = dict(zip(df_summary["cluster_id"], df_summary["is_single"]))
|
| 512 |
+
else:
|
| 513 |
+
is_single_dict = {cid: False for cid in cluster_ids_sorted}
|
| 514 |
+
single_nodes = [n for n, data in G.nodes(data=True) if is_single_dict.get(data['cluster'], False)]
|
| 515 |
+
non_single_nodes = [n for n in G.nodes() if n not in single_nodes]
|
| 516 |
+
|
| 517 |
+
weights = [G[a][b][weight_mode] for a, b in G.edges()]
|
| 518 |
+
if weights:
|
| 519 |
+
w_arr = np.array(weights)
|
| 520 |
+
w_arr = np.log1p(w_arr)
|
| 521 |
+
wmin, wmax = w_arr.min(), w_arr.max()
|
| 522 |
+
def scale(w):
|
| 523 |
+
lw = np.log1p(w)
|
| 524 |
+
if wmax > wmin:
|
| 525 |
+
return EDGE_WIDTH_BASE + (EDGE_WIDTH_MAX - EDGE_WIDTH_BASE) * ((lw - wmin) / (wmax - wmin))
|
| 526 |
+
else:
|
| 527 |
+
return (EDGE_WIDTH_BASE + EDGE_WIDTH_MAX) / 2
|
| 528 |
+
else:
|
| 529 |
+
scale = lambda w: EDGE_WIDTH_BASE
|
| 530 |
+
|
| 531 |
+
edge_traces = []
|
| 532 |
+
for a, b in G.edges():
|
| 533 |
+
if not show_singles and (a in single_nodes or b in single_nodes):
|
| 534 |
+
continue
|
| 535 |
+
w = G[a][b][weight_mode]
|
| 536 |
+
width = scale(w)
|
| 537 |
+
x0, y0 = pos[a]
|
| 538 |
+
x1, y1 = pos[b]
|
| 539 |
+
edge_traces.append(
|
| 540 |
+
go.Scatter(
|
| 541 |
+
x=[x0, x1], y=[y0, y1],
|
| 542 |
+
mode='lines',
|
| 543 |
+
line=dict(width=width, color='#888'),
|
| 544 |
+
opacity=EDGE_ALPHA,
|
| 545 |
+
hoverinfo='skip',
|
| 546 |
+
showlegend=False,
|
| 547 |
+
)
|
| 548 |
+
)
|
| 549 |
+
|
| 550 |
+
node_sizes_raw = {}
|
| 551 |
+
for n in G.nodes():
|
| 552 |
+
if weight_mode == "count":
|
| 553 |
+
node_sizes_raw[n] = df[df['author_id'] == n]['pub_id'].nunique()
|
| 554 |
+
else:
|
| 555 |
+
node_sizes_raw[n] = df[df['author_id'] == n]['fract_author_affiliation_value'].sum()
|
| 556 |
+
node_size_values = np.array(list(node_sizes_raw.values()))
|
| 557 |
+
ns_min, ns_max = node_size_values.min(), node_size_values.max() if len(node_size_values) > 0 else (0, 1)
|
| 558 |
+
|
| 559 |
+
def scale_node_size(v):
|
| 560 |
+
if ns_max > ns_min:
|
| 561 |
+
norm = (v - ns_min) / (ns_max - ns_min)
|
| 562 |
+
else:
|
| 563 |
+
norm = 0.5
|
| 564 |
+
if node_size_scale_mode == "area":
|
| 565 |
+
min_area = np.pi * (NODE_SIZE_BASE / 2) ** 2
|
| 566 |
+
max_area = np.pi * (NODE_SIZE_MAX / 2) ** 2
|
| 567 |
+
area = min_area + (max_area - min_area) * norm
|
| 568 |
+
diameter = 2 * np.sqrt(area / np.pi)
|
| 569 |
+
return diameter
|
| 570 |
+
else: # "diameter"
|
| 571 |
+
return NODE_SIZE_BASE + (NODE_SIZE_MAX - NODE_SIZE_BASE) * norm
|
| 572 |
+
|
| 573 |
+
node_x, node_y, node_color, node_text, node_size = [], [], [], [], []
|
| 574 |
+
for node in non_single_nodes:
|
| 575 |
+
x, y = pos[node]
|
| 576 |
+
cluster_id = G.nodes[node]['cluster']
|
| 577 |
+
color = cluster_color_map.get(cluster_id, "#ccc")
|
| 578 |
+
n_pubs = df[df['author_id'] == node]['pub_id'].nunique()
|
| 579 |
+
n_value = df[df['author_id'] == node]['fract_author_affiliation_value'].sum()
|
| 580 |
+
author_short = author_id2short.get(node, str(node))
|
| 581 |
+
node_x.append(x)
|
| 582 |
+
node_y.append(y)
|
| 583 |
+
node_color.append(color)
|
| 584 |
+
node_text.append(
|
| 585 |
+
f"Авторский кластер: {int(cluster_id)}<br>Автор: {author_short}"
|
| 586 |
+
f"<br>Публикаций: {n_pubs}"
|
| 587 |
+
f"<br>Продуктивность: {n_value:.2f}"
|
| 588 |
+
)
|
| 589 |
+
sz = node_sizes_raw[node]
|
| 590 |
+
node_size.append(scale_node_size(sz))
|
| 591 |
+
node_trace = go.Scatter(
|
| 592 |
+
x=node_x, y=node_y,
|
| 593 |
+
mode='markers',
|
| 594 |
+
hoverinfo='text',
|
| 595 |
+
text=node_text,
|
| 596 |
+
marker=dict(
|
| 597 |
+
showscale=False,
|
| 598 |
+
color=node_color,
|
| 599 |
+
size=node_size,
|
| 600 |
+
line_width=1
|
| 601 |
+
),
|
| 602 |
+
name="Кластеры"
|
| 603 |
+
)
|
| 604 |
+
|
| 605 |
+
single_x, single_y, single_color, single_text, single_size = [], [], [], [], []
|
| 606 |
+
for node in single_nodes:
|
| 607 |
+
x, y = pos[node]
|
| 608 |
+
cluster_id = G.nodes[node]['cluster']
|
| 609 |
+
color = cluster_color_map.get(cluster_id, "#ccc")
|
| 610 |
+
n_pubs = df[df['author_id'] == node]['pub_id'].nunique()
|
| 611 |
+
n_value = df[df['author_id'] == node]['fract_author_affiliation_value'].sum()
|
| 612 |
+
author_short = author_id2short.get(node, str(node))
|
| 613 |
+
single_x.append(x)
|
| 614 |
+
single_y.append(y)
|
| 615 |
+
single_color.append(color)
|
| 616 |
+
single_text.append(
|
| 617 |
+
f"Моноавторский кластер: {int(cluster_id)}<br>Автор: {author_short}"
|
| 618 |
+
f"<br>Публикаций: {n_pubs}"
|
| 619 |
+
f"<br>Продуктивность: {n_value:.2f}"
|
| 620 |
+
)
|
| 621 |
+
sz = node_sizes_raw[node]
|
| 622 |
+
single_size.append(scale_node_size(sz))
|
| 623 |
+
single_node_trace = go.Scatter(
|
| 624 |
+
x=single_x, y=single_y,
|
| 625 |
+
mode='markers',
|
| 626 |
+
hoverinfo='text',
|
| 627 |
+
text=single_text,
|
| 628 |
+
marker=dict(
|
| 629 |
+
showscale=False,
|
| 630 |
+
color='rgba(0,0,0,0)',
|
| 631 |
+
size=single_size,
|
| 632 |
+
line=dict(width=SINGLE_NODE_BORDER_WIDTH, color=single_color)
|
| 633 |
+
),
|
| 634 |
+
name="Одиночные авторы",
|
| 635 |
+
visible=show_singles
|
| 636 |
+
)
|
| 637 |
+
|
| 638 |
+
traces = edge_traces + [node_trace]
|
| 639 |
+
if show_singles and len(single_nodes) > 0:
|
| 640 |
+
traces.append(single_node_trace)
|
| 641 |
+
|
| 642 |
+
fig = go.Figure(
|
| 643 |
+
data=traces,
|
| 644 |
+
layout=go.Layout(
|
| 645 |
+
showlegend=False,
|
| 646 |
+
hovermode='closest',
|
| 647 |
+
margin=dict(b=10, l=10, r=10, t=10),
|
| 648 |
+
xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
|
| 649 |
+
yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
|
| 650 |
+
template="plotly_white"
|
| 651 |
+
)
|
| 652 |
+
)
|
| 653 |
+
return fig
|
| 654 |
+
|
| 655 |
+
def shorten_text(s, max_len=60):
|
| 656 |
+
if not isinstance(s, str) or len(s) <= max_len:
|
| 657 |
+
return s
|
| 658 |
+
cut = s[:max_len]
|
| 659 |
+
if " " in cut:
|
| 660 |
+
cut = cut[:cut.rfind(" ")]
|
| 661 |
+
return cut.strip() + " ..."
|
| 662 |
+
|
| 663 |
+
# ========== LAYOUT И CALLBACKS =============
|
| 664 |
+
|
| 665 |
+
# Подготовка данных для продуктивности (делается единожды)
|
| 666 |
+
df_prod, multi_affil_prod = load_and_prepare_data(YEAR_START, YEAR_END, ORG_ID)
|
| 667 |
+
|
| 668 |
+
app = dash.Dash(
|
| 669 |
+
__name__,
|
| 670 |
+
title="Вузометрия.РФ",
|
| 671 |
+
update_title="Загрузка...",
|
| 672 |
+
meta_tags=[
|
| 673 |
+
{"name": "description", "content": "Вузометрия.РФ – измеряем университеты"}
|
| 674 |
+
]
|
| 675 |
+
)
|
| 676 |
+
|
| 677 |
+
app.layout = html.Div([
|
| 678 |
+
# Верхний заголовок
|
| 679 |
+
html.Div(
|
| 680 |
+
"Московский государственный институт электроники и математики (МИЭМ) НИУ ВШЭ",
|
| 681 |
+
style={
|
| 682 |
+
"fontFamily": "Arial, sans-serif",
|
| 683 |
+
"fontSize": "22px",
|
| 684 |
+
"fontWeight": "bold",
|
| 685 |
+
"textAlign": "center",
|
| 686 |
+
"color": "#123157",
|
| 687 |
+
"padding": "22px 0 4px 0",
|
| 688 |
+
}
|
| 689 |
+
),
|
| 690 |
+
|
| 691 |
+
# === График продуктивности с подложкой ===
|
| 692 |
+
html.Div([
|
| 693 |
+
html.H4(
|
| 694 |
+
"Динамика публикационной продуктивности",
|
| 695 |
+
style={
|
| 696 |
+
"margin-bottom": "12px",
|
| 697 |
+
"marginTop": "6px",
|
| 698 |
+
"font-family": "Arial, sans-serif",
|
| 699 |
+
"font-weight": "bold",
|
| 700 |
+
"text-align": "center",
|
| 701 |
+
"font-size": "20px",
|
| 702 |
+
"color": "#22335b",
|
| 703 |
+
}
|
| 704 |
+
),
|
| 705 |
+
dcc.Loading(
|
| 706 |
+
id="loading-productivity-graph",
|
| 707 |
+
type="circle",
|
| 708 |
+
color="#22335b",
|
| 709 |
+
children=[
|
| 710 |
+
dcc.Graph(
|
| 711 |
+
id='productivity-graph',
|
| 712 |
+
figure=build_productivity_figure(df_prod, multi_affil_prod),
|
| 713 |
+
style={
|
| 714 |
+
"width": "100%",
|
| 715 |
+
"height": "470px",
|
| 716 |
+
"padding": "0"
|
| 717 |
+
},
|
| 718 |
+
config={
|
| 719 |
+
"displaylogo": False,
|
| 720 |
+
"modeBarButtonsToRemove": ["sendDataToCloud"]
|
| 721 |
+
}
|
| 722 |
+
),
|
| 723 |
+
]
|
| 724 |
+
),
|
| 725 |
+
], style={
|
| 726 |
+
'background': '#fff',
|
| 727 |
+
'border-radius': '18px',
|
| 728 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 729 |
+
'padding': '22px 12px 12px 12px',
|
| 730 |
+
'width': '90%',
|
| 731 |
+
'margin': '20px auto 20px auto'
|
| 732 |
+
}),
|
| 733 |
+
|
| 734 |
+
dcc.Store(id='sidebar-state', data={'show': False}),
|
| 735 |
+
# Кнопка-гамбургер
|
| 736 |
+
html.Button('☰', id='toggle-sidebar', n_clicks=0, style={
|
| 737 |
+
"fontSize": "24px",
|
| 738 |
+
"margin": "0 0 0 2px",
|
| 739 |
+
"padding": "2px 2px",
|
| 740 |
+
'position': 'fixed',
|
| 741 |
+
'top': '0px',
|
| 742 |
+
'left': '0px',
|
| 743 |
+
'zIndex': 1102
|
| 744 |
+
}),
|
| 745 |
+
# Сайдбар
|
| 746 |
+
html.Div([
|
| 747 |
+
html.Img(
|
| 748 |
+
src='/assets/logo.png',
|
| 749 |
+
style={
|
| 750 |
+
"width": "110px",
|
| 751 |
+
"margin": "0 auto",
|
| 752 |
+
"display": "block",
|
| 753 |
+
"marginBottom": "8px"
|
| 754 |
+
}
|
| 755 |
+
),
|
| 756 |
+
html.Div(
|
| 757 |
+
"Вузометрия.РФ",
|
| 758 |
+
style={
|
| 759 |
+
"fontFamily": "Arial, sans-serif",
|
| 760 |
+
"fontSize": "22px",
|
| 761 |
+
"fontWeight": "bold",
|
| 762 |
+
"textAlign": "center",
|
| 763 |
+
"color": "#22335b",
|
| 764 |
+
"marginBottom": "2px"
|
| 765 |
+
}
|
| 766 |
+
),
|
| 767 |
+
html.Div(
|
| 768 |
+
"Вы опрашиваете? Мы — измеряем",
|
| 769 |
+
style={
|
| 770 |
+
"fontFamily": "Arial, sans-serif",
|
| 771 |
+
"fontSize": "13px",
|
| 772 |
+
"fontWeight": "normal",
|
| 773 |
+
"textAlign": "center",
|
| 774 |
+
"color": "#666",
|
| 775 |
+
"marginBottom": "7px"
|
| 776 |
+
}
|
| 777 |
+
),
|
| 778 |
+
html.H3("Общие настройки", style={
|
| 779 |
+
"margin-bottom": "10px",
|
| 780 |
+
"fontSize": "15px",
|
| 781 |
+
"fontWeight": "bold",
|
| 782 |
+
"marginTop": "10px"
|
| 783 |
+
}),
|
| 784 |
+
html.Label("Организация:", style={
|
| 785 |
+
"margin-bottom": "3px",
|
| 786 |
+
"fontSize": "13px"
|
| 787 |
+
}),
|
| 788 |
+
dcc.Dropdown(
|
| 789 |
+
id='org-dropdown',
|
| 790 |
+
options=[{"label": "МИЭМ НИУ ВШЭ", "value": "miem_hse"}],
|
| 791 |
+
value="miem_hse",
|
| 792 |
+
style={'width': '100%', "margin-bottom": "7px", "fontSize": "13px"},
|
| 793 |
+
searchable=False,
|
| 794 |
+
clearable=False,
|
| 795 |
+
disabled=True
|
| 796 |
+
),
|
| 797 |
+
html.Label("Период:", style={
|
| 798 |
+
"margin-bottom": "3px",
|
| 799 |
+
"fontSize": "13px"
|
| 800 |
+
}),
|
| 801 |
+
dcc.Dropdown(
|
| 802 |
+
id='period-dropdown',
|
| 803 |
+
options=[{"label": p["label"], "value": p["key"]} for p in PERIODS],
|
| 804 |
+
value=PERIODS[2]["key"],
|
| 805 |
+
style={'width': '100%', "margin-bottom": "13px", "fontSize": "13px"},
|
| 806 |
+
searchable=False,
|
| 807 |
+
clearable=False
|
| 808 |
+
),
|
| 809 |
+
html.Div([
|
| 810 |
+
html.Span(
|
| 811 |
+
"© Антон Лощилов, 2025",
|
| 812 |
+
style={
|
| 813 |
+
"fontFamily": "Arial, sans-serif",
|
| 814 |
+
"fontSize": "11px",
|
| 815 |
+
"color": "#aaa"
|
| 816 |
+
}
|
| 817 |
+
),
|
| 818 |
+
html.Span(
|
| 819 |
+
"v. 0.10",
|
| 820 |
+
style={
|
| 821 |
+
"fontFamily": "Arial, sans-serif",
|
| 822 |
+
"fontSize": "11.5px",
|
| 823 |
+
"fontWeight": "bold",
|
| 824 |
+
"color": "#aaa"
|
| 825 |
+
}
|
| 826 |
+
),
|
| 827 |
+
], style={
|
| 828 |
+
"position": "absolute",
|
| 829 |
+
"bottom": "10px",
|
| 830 |
+
"left": "0",
|
| 831 |
+
"right": "0",
|
| 832 |
+
"width": "92%",
|
| 833 |
+
"margin": "0 4%",
|
| 834 |
+
"display": "flex",
|
| 835 |
+
"flexDirection": "row",
|
| 836 |
+
"justifyContent": "space-between"
|
| 837 |
+
})
|
| 838 |
+
], id='sidebar-content', style={
|
| 839 |
+
'width': '310px',
|
| 840 |
+
'padding': '18px 16px 18px 16px',
|
| 841 |
+
'background': '#f8f8f8',
|
| 842 |
+
'border-radius': '18px',
|
| 843 |
+
'box-shadow': '0 0 22px #ccc8',
|
| 844 |
+
'font-family': 'Arial, sans-serif',
|
| 845 |
+
'font-size': '13px',
|
| 846 |
+
'overflowY': 'auto',
|
| 847 |
+
'zIndex': 1101,
|
| 848 |
+
'position': 'fixed',
|
| 849 |
+
'top': '60px',
|
| 850 |
+
'left': '18px',
|
| 851 |
+
'minHeight': '450px',
|
| 852 |
+
'maxHeight': '95vh',
|
| 853 |
+
'transition': 'opacity 0.35s, pointer-events 0.35s',
|
| 854 |
+
'opacity': 0,
|
| 855 |
+
'pointerEvents': 'none',
|
| 856 |
+
'display': 'none'
|
| 857 |
+
}
|
| 858 |
+
),
|
| 859 |
+
|
| 860 |
+
# === Основное содержимое страницы ===
|
| 861 |
+
html.Div([
|
| 862 |
+
# --- 1. ГРНТИ-карта (тримап) ---
|
| 863 |
+
html.Div([
|
| 864 |
+
html.H4(id='grnti-main-title', style={
|
| 865 |
+
"margin-bottom": "12px",
|
| 866 |
+
"marginTop": "6px",
|
| 867 |
+
"font-family": "Arial, sans-serif",
|
| 868 |
+
"font-weight": "bold",
|
| 869 |
+
"text-align": "center",
|
| 870 |
+
"font-size": "20px",
|
| 871 |
+
"color": "#22335b",
|
| 872 |
+
}),
|
| 873 |
+
html.Div([
|
| 874 |
+
html.Label("Тип взвешивания:", style={
|
| 875 |
+
"marginRight": "12px",
|
| 876 |
+
"fontFamily": 'Open Sans, Arial, sans-serif',
|
| 877 |
+
"fontSize": "14px",
|
| 878 |
+
"whiteSpace": "nowrap"
|
| 879 |
+
}),
|
| 880 |
+
dcc.RadioItems(
|
| 881 |
+
id='grnti-norm-mode',
|
| 882 |
+
options=[
|
| 883 |
+
{'label': 'По продуктивности', 'value': 'value'},
|
| 884 |
+
{'label': 'По числу публикаций', 'value': 'frac_npubs'},
|
| 885 |
+
],
|
| 886 |
+
value='value',
|
| 887 |
+
labelStyle={'display': 'inline-block', 'margin-right': '16px', 'fontSize': '14px', 'fontFamily': 'Arial, sans-serif'},
|
| 888 |
+
inputStyle={"margin-right": "5px"},
|
| 889 |
+
style={'display': 'inline-block'}
|
| 890 |
+
),
|
| 891 |
+
], style={
|
| 892 |
+
"display": "flex",
|
| 893 |
+
"alignItems": "center",
|
| 894 |
+
"gap": "8px",
|
| 895 |
+
"marginBottom": "5px",
|
| 896 |
+
"marginLeft": "18px"
|
| 897 |
+
}),
|
| 898 |
+
dcc.Loading(
|
| 899 |
+
id="loading-grnti-treemap",
|
| 900 |
+
type="circle",
|
| 901 |
+
color="#22335b",
|
| 902 |
+
children=[
|
| 903 |
+
dcc.Graph(
|
| 904 |
+
id='grnti-treemap-graph',
|
| 905 |
+
style={'width': '100%'},
|
| 906 |
+
config={
|
| 907 |
+
'displayModeBar': True,
|
| 908 |
+
'displaylogo': False
|
| 909 |
+
}
|
| 910 |
+
)
|
| 911 |
+
]
|
| 912 |
+
),
|
| 913 |
+
], style={
|
| 914 |
+
'background': '#fff',
|
| 915 |
+
'border-radius': '18px',
|
| 916 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 917 |
+
'padding': '22px 12px 12px 12px',
|
| 918 |
+
'width': '90%',
|
| 919 |
+
'margin': '20px auto 20px auto',
|
| 920 |
+
}),
|
| 921 |
+
|
| 922 |
+
# --- 2. Карта соавторства ---
|
| 923 |
+
html.Div([
|
| 924 |
+
html.H4(id='main-title', style={
|
| 925 |
+
"margin-bottom": "12px",
|
| 926 |
+
"marginTop": "6px",
|
| 927 |
+
"font-family": "Arial, sans-serif",
|
| 928 |
+
"font-weight": "bold",
|
| 929 |
+
"text-align": "center",
|
| 930 |
+
"font-size": "20px",
|
| 931 |
+
"color": "#22335b",
|
| 932 |
+
}),
|
| 933 |
+
html.Div([
|
| 934 |
+
html.Label("Тип взвешивания:", style={
|
| 935 |
+
"margin-bottom": "0",
|
| 936 |
+
"font-family": "Arial, sans-serif",
|
| 937 |
+
"font-size": "14px"
|
| 938 |
+
}),
|
| 939 |
+
html.Div([
|
| 940 |
+
dcc.RadioItems(
|
| 941 |
+
id='weight-mode',
|
| 942 |
+
options=[
|
| 943 |
+
{"label": "По продуктивности", "value": "value"},
|
| 944 |
+
{"label": "По числу публикаций", "value": "count"}
|
| 945 |
+
],
|
| 946 |
+
value="value",
|
| 947 |
+
labelStyle={'display': 'inline-block', 'margin-right': '16px'},
|
| 948 |
+
inputStyle={"margin-right": "4px"},
|
| 949 |
+
style={"margin-bottom": "0"}
|
| 950 |
+
),
|
| 951 |
+
dcc.Checklist(
|
| 952 |
+
id='show-singles',
|
| 953 |
+
options=[{"label": "Показывать одиночных авторов", "value": "show"}],
|
| 954 |
+
value=[],
|
| 955 |
+
style={
|
| 956 |
+
"margin-left": "28px",
|
| 957 |
+
"font-family": "Arial, sans-serif",
|
| 958 |
+
"font-size": "14px",
|
| 959 |
+
"display": "inline-block",
|
| 960 |
+
"verticalAlign": "middle"
|
| 961 |
+
},
|
| 962 |
+
inputStyle={"margin-right": "4px"}
|
| 963 |
+
),
|
| 964 |
+
], style={
|
| 965 |
+
"display": "flex",
|
| 966 |
+
"alignItems": "center",
|
| 967 |
+
"margin-bottom": "10px"
|
| 968 |
+
}),
|
| 969 |
+
], style={
|
| 970 |
+
"margin-bottom": "18px",
|
| 971 |
+
"margin-left": "14px"
|
| 972 |
+
}),
|
| 973 |
+
dcc.Loading(
|
| 974 |
+
id="loading-cluster-graph",
|
| 975 |
+
type="circle",
|
| 976 |
+
color="#22335b",
|
| 977 |
+
children=[
|
| 978 |
+
dcc.Graph(
|
| 979 |
+
id='cluster-graph',
|
| 980 |
+
style={"width": "100%"},
|
| 981 |
+
config={
|
| 982 |
+
'displaylogo': False,
|
| 983 |
+
'modeBarButtonsToRemove': ['sendDataToCloud']
|
| 984 |
+
}
|
| 985 |
+
)
|
| 986 |
+
]
|
| 987 |
+
),
|
| 988 |
+
], style={
|
| 989 |
+
'background': '#fff',
|
| 990 |
+
'border-radius': '18px',
|
| 991 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 992 |
+
'padding': '22px 12px 12px 12px',
|
| 993 |
+
'width': '90%',
|
| 994 |
+
'margin': '20px auto 20px auto'
|
| 995 |
+
}),
|
| 996 |
+
|
| 997 |
+
# --- 3. Семантическая карта ---
|
| 998 |
+
html.Div([
|
| 999 |
+
html.H4(
|
| 1000 |
+
id='science-map-title',
|
| 1001 |
+
style={
|
| 1002 |
+
"margin-bottom": "12px",
|
| 1003 |
+
"marginTop": "6px",
|
| 1004 |
+
"font-family": "Arial, sans-serif",
|
| 1005 |
+
"font-weight": "bold",
|
| 1006 |
+
"text-align": "center",
|
| 1007 |
+
"font-size": "20px",
|
| 1008 |
+
"color": "#22335b",
|
| 1009 |
+
}
|
| 1010 |
+
),
|
| 1011 |
+
html.Div([
|
| 1012 |
+
html.Label("Размер маркера:", style={
|
| 1013 |
+
"fontFamily": "Arial, sans-serif",
|
| 1014 |
+
"fontSize": "14px",
|
| 1015 |
+
"marginRight": "8px",
|
| 1016 |
+
"whiteSpace": "nowrap"
|
| 1017 |
+
}),
|
| 1018 |
+
dcc.Dropdown(
|
| 1019 |
+
id='size-dropdown',
|
| 1020 |
+
options=[
|
| 1021 |
+
{'label': 'Общая продуктивность', 'value': 'value'},
|
| 1022 |
+
{'label': 'Вклад организации', 'value': 'org_value'}
|
| 1023 |
+
],
|
| 1024 |
+
value='value',
|
| 1025 |
+
style={
|
| 1026 |
+
"fontFamily": "Arial, sans-serif",
|
| 1027 |
+
"fontSize": "14px",
|
| 1028 |
+
"width": "250px",
|
| 1029 |
+
"marginRight": "30px"
|
| 1030 |
+
},
|
| 1031 |
+
searchable=False,
|
| 1032 |
+
clearable=False
|
| 1033 |
+
),
|
| 1034 |
+
html.Label("Легенда:", style={
|
| 1035 |
+
"fontFamily": "Arial, sans-serif",
|
| 1036 |
+
"fontSize": "14px",
|
| 1037 |
+
"marginRight": "8px",
|
| 1038 |
+
"whiteSpace": "nowrap"
|
| 1039 |
+
}),
|
| 1040 |
+
dcc.Dropdown(
|
| 1041 |
+
id='color-dropdown',
|
| 1042 |
+
options=[
|
| 1043 |
+
{'label': 'Авторские кластеры', 'value': 'author_cluster_id'},
|
| 1044 |
+
{'label': 'Семантические кластеры', 'value': 'semantic_cluster_id'}
|
| 1045 |
+
],
|
| 1046 |
+
value='author_cluster_id',
|
| 1047 |
+
style={
|
| 1048 |
+
"fontFamily": "Arial, sans-serif",
|
| 1049 |
+
"fontSize": "14px",
|
| 1050 |
+
"width": "250px"
|
| 1051 |
+
},
|
| 1052 |
+
searchable=False,
|
| 1053 |
+
clearable=False
|
| 1054 |
+
),
|
| 1055 |
+
], style={
|
| 1056 |
+
"display": "flex",
|
| 1057 |
+
"flexDirection": "row",
|
| 1058 |
+
"alignItems": "center",
|
| 1059 |
+
"marginBottom": "18px"
|
| 1060 |
+
}),
|
| 1061 |
+
html.Div([
|
| 1062 |
+
dcc.Loading(
|
| 1063 |
+
id="loading-science-map-plot",
|
| 1064 |
+
type="circle",
|
| 1065 |
+
color="#22335b",
|
| 1066 |
+
children=[
|
| 1067 |
+
dcc.Graph(
|
| 1068 |
+
id='science-map-plot',
|
| 1069 |
+
style={"width": "100%", "height": "850px"},
|
| 1070 |
+
config={
|
| 1071 |
+
'displaylogo': False,
|
| 1072 |
+
'modeBarButtonsToRemove': ['sendDataToCloud']
|
| 1073 |
+
}
|
| 1074 |
+
)
|
| 1075 |
+
]
|
| 1076 |
+
)
|
| 1077 |
+
], style={
|
| 1078 |
+
"width": "65%",
|
| 1079 |
+
"display": "inline-block",
|
| 1080 |
+
"verticalAlign": "top"
|
| 1081 |
+
}),
|
| 1082 |
+
html.Div([
|
| 1083 |
+
html.Div([
|
| 1084 |
+
html.Div(id='detail-title'),
|
| 1085 |
+
html.Div(id='detail-table')
|
| 1086 |
+
], style={
|
| 1087 |
+
'background': '#fafbfc',
|
| 1088 |
+
'border-radius': '16px',
|
| 1089 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 1090 |
+
'padding': '18px 14px 12px 14px',
|
| 1091 |
+
'margin-top': '18px',
|
| 1092 |
+
'font-size': '14px',
|
| 1093 |
+
'height': '800px',
|
| 1094 |
+
'overflowY': 'auto',
|
| 1095 |
+
'display': 'flex',
|
| 1096 |
+
'flexDirection': 'column'
|
| 1097 |
+
})
|
| 1098 |
+
], style={
|
| 1099 |
+
"width": "30%",
|
| 1100 |
+
"display": "inline-block",
|
| 1101 |
+
"verticalAlign": "top",
|
| 1102 |
+
"paddingLeft": "24px"
|
| 1103 |
+
})
|
| 1104 |
+
], style={
|
| 1105 |
+
'background': '#fff',
|
| 1106 |
+
'padding': '22px 12px 12px 12px',
|
| 1107 |
+
'border-radius': '18px',
|
| 1108 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 1109 |
+
'width': '90%',
|
| 1110 |
+
'margin': '20px auto 20px auto'
|
| 1111 |
+
}),
|
| 1112 |
+
|
| 1113 |
+
# --- 4. Bar-график ---
|
| 1114 |
+
html.Div([
|
| 1115 |
+
html.H4(id='bar-title', style={
|
| 1116 |
+
"margin-bottom": "12px",
|
| 1117 |
+
"marginTop": "6px",
|
| 1118 |
+
"font-family": "Arial, sans-serif",
|
| 1119 |
+
"font-weight": "bold",
|
| 1120 |
+
"text-align": "center",
|
| 1121 |
+
"font-size": "20px",
|
| 1122 |
+
"color": "#22335b",
|
| 1123 |
+
}),
|
| 1124 |
+
html.Div([
|
| 1125 |
+
html.Span("Сортировка:", style={
|
| 1126 |
+
"marginRight": "10px",
|
| 1127 |
+
"fontFamily": 'Open Sans, Arial, sans-serif',
|
| 1128 |
+
"fontSize": "14px"
|
| 1129 |
+
}),
|
| 1130 |
+
dcc.Dropdown(
|
| 1131 |
+
id='sort-dropdown',
|
| 1132 |
+
options=[
|
| 1133 |
+
{'label': 'по ядру организации', 'value': 'hse'},
|
| 1134 |
+
{'label': 'по ядру организации и совместителям', 'value': 'hse_plus_2th'},
|
| 1135 |
+
{'label': 'по суммарной продуктивности', 'value': 'sum'}
|
| 1136 |
+
],
|
| 1137 |
+
value='hse',
|
| 1138 |
+
searchable=False,
|
| 1139 |
+
clearable=False,
|
| 1140 |
+
style={
|
| 1141 |
+
'width': '280px',
|
| 1142 |
+
'fontFamily': 'Open Sans, Arial, sans-serif',
|
| 1143 |
+
'fontSize': '14px',
|
| 1144 |
+
'verticalAlign': 'middle'
|
| 1145 |
+
}
|
| 1146 |
+
),
|
| 1147 |
+
], style={
|
| 1148 |
+
"display": "flex",
|
| 1149 |
+
"flexDirection": "row",
|
| 1150 |
+
"alignItems": "center",
|
| 1151 |
+
"marginBottom": "4px"
|
| 1152 |
+
}),
|
| 1153 |
+
dcc.Loading(
|
| 1154 |
+
id="loading-bar-graph",
|
| 1155 |
+
type="circle",
|
| 1156 |
+
color="#22335b",
|
| 1157 |
+
children=[
|
| 1158 |
+
dcc.Graph(
|
| 1159 |
+
id='bar-graph',
|
| 1160 |
+
style={'width': '100%'},
|
| 1161 |
+
config={
|
| 1162 |
+
'displaylogo': False,
|
| 1163 |
+
'modeBarButtonsToRemove': ['sendDataToCloud']
|
| 1164 |
+
}
|
| 1165 |
+
)
|
| 1166 |
+
]
|
| 1167 |
+
),
|
| 1168 |
+
], style={
|
| 1169 |
+
'background': '#fff',
|
| 1170 |
+
'border-radius': '18px',
|
| 1171 |
+
'box-shadow': '0 0 8px #ccc4',
|
| 1172 |
+
'padding': '22px 12px 12px 12px',
|
| 1173 |
+
'width': '90%',
|
| 1174 |
+
'margin': '20px auto 20px auto'
|
| 1175 |
+
}),
|
| 1176 |
+
|
| 1177 |
+
# --- Кнопка ОТЧЕТ и Download ---
|
| 1178 |
+
html.Div([
|
| 1179 |
+
html.Button(
|
| 1180 |
+
"ОТЧЕТ",
|
| 1181 |
+
id="download-report-btn",
|
| 1182 |
+
className="fancy-download-btn",
|
| 1183 |
+
),
|
| 1184 |
+
dcc.Download(id="download-report"),
|
| 1185 |
+
], style={
|
| 1186 |
+
"width": "100%",
|
| 1187 |
+
"textAlign": "center",
|
| 1188 |
+
"marginBottom": "0"
|
| 1189 |
+
}),
|
| 1190 |
+
], id='main-content', style={
|
| 1191 |
+
'width': '100%',
|
| 1192 |
+
'paddingLeft': '0',
|
| 1193 |
+
'transition': 'none'
|
| 1194 |
+
}),
|
| 1195 |
+
], style={
|
| 1196 |
+
'width': '100%',
|
| 1197 |
+
'overflowX': 'hidden',
|
| 1198 |
+
'position': 'relative',
|
| 1199 |
+
'minHeight': '100vh',
|
| 1200 |
+
'background': '#fcfcfc'
|
| 1201 |
+
})
|
| 1202 |
+
|
| 1203 |
+
|
| 1204 |
+
|
| 1205 |
+
# === GRNTI-TreeMap ===
|
| 1206 |
+
@app.callback(
|
| 1207 |
+
Output('grnti-treemap-graph', 'figure'),
|
| 1208 |
+
Output('grnti-main-title', 'children'),
|
| 1209 |
+
Input('period-dropdown', 'value'),
|
| 1210 |
+
Input('grnti-norm-mode', 'value')
|
| 1211 |
+
)
|
| 1212 |
+
def update_grnti_treemap(period_value, norm_mode):
|
| 1213 |
+
period = next((p for p in PERIODS if p['key'] == period_value), PERIODS[0])
|
| 1214 |
+
df = grnti_load_df_by_period(period['key'])
|
| 1215 |
+
title = f"Карта рубрик ГРНТИ ({period['label']})"
|
| 1216 |
+
fig = grnti_make_treemap(df, norm_mode)
|
| 1217 |
+
return fig, title
|
| 1218 |
+
|
| 1219 |
+
# === Sidebar ===
|
| 1220 |
+
@app.callback(
|
| 1221 |
+
Output('sidebar-content', 'style'),
|
| 1222 |
+
Output('sidebar-state', 'data'),
|
| 1223 |
+
Input('toggle-sidebar', 'n_clicks'),
|
| 1224 |
+
State('sidebar-state', 'data'),
|
| 1225 |
+
prevent_initial_call=True
|
| 1226 |
+
)
|
| 1227 |
+
def toggle_sidebar(n_clicks, sidebar_state):
|
| 1228 |
+
show = not sidebar_state.get('show', False)
|
| 1229 |
+
base_style = {
|
| 1230 |
+
'width': '310px',
|
| 1231 |
+
'padding': '18px 16px 18px 16px',
|
| 1232 |
+
'background': '#f8f8f8',
|
| 1233 |
+
'border-radius': '18px',
|
| 1234 |
+
'box-shadow': '0 0 22px #ccc8',
|
| 1235 |
+
'font-family': 'Arial, sans-serif',
|
| 1236 |
+
'font-size': '13px',
|
| 1237 |
+
'overflowY': 'auto',
|
| 1238 |
+
'zIndex': 1101,
|
| 1239 |
+
'transition': 'opacity 0.35s, pointer-events 0.35s',
|
| 1240 |
+
'position': 'fixed',
|
| 1241 |
+
'top': '60px',
|
| 1242 |
+
'left': '18px',
|
| 1243 |
+
'minHeight': '450px',
|
| 1244 |
+
'maxHeight': '95vh'
|
| 1245 |
+
}
|
| 1246 |
+
if show:
|
| 1247 |
+
base_style['opacity'] = 1
|
| 1248 |
+
base_style['pointerEvents'] = 'auto'
|
| 1249 |
+
base_style['display'] = 'block'
|
| 1250 |
+
else:
|
| 1251 |
+
base_style['opacity'] = 0
|
| 1252 |
+
base_style['pointerEvents'] = 'none'
|
| 1253 |
+
base_style['display'] = 'none'
|
| 1254 |
+
return base_style, {'show': show}
|
| 1255 |
+
|
| 1256 |
+
# === Кластеры и bar ===
|
| 1257 |
+
@app.callback(
|
| 1258 |
+
Output('main-title', 'children'),
|
| 1259 |
+
Output('cluster-graph', 'figure'),
|
| 1260 |
+
Output('bar-title', 'children'),
|
| 1261 |
+
Output('bar-graph', 'figure'),
|
| 1262 |
+
Input('period-dropdown', 'value'),
|
| 1263 |
+
Input('weight-mode', 'value'),
|
| 1264 |
+
Input('show-singles', 'value'),
|
| 1265 |
+
Input('sort-dropdown', 'value'),
|
| 1266 |
+
)
|
| 1267 |
+
def update_graphs(period_key, weight_mode, show_singles, sort_by):
|
| 1268 |
+
period = next((p for p in PERIODS if p['key'] == period_key), PERIODS[0])
|
| 1269 |
+
period_years = period["label"]
|
| 1270 |
+
main_title = f"Карта соавторства ({period_years})"
|
| 1271 |
+
bar_title = f"Продуктивность авторских кластеров ({period_years})"
|
| 1272 |
+
df, df_summary = load_cluster_data(period['key'])
|
| 1273 |
+
show_singles_flag = "show" in (show_singles if show_singles else [])
|
| 1274 |
+
fig = plotly_network_graph(
|
| 1275 |
+
df, df_summary,
|
| 1276 |
+
weight_mode=weight_mode,
|
| 1277 |
+
show_singles=show_singles_flag,
|
| 1278 |
+
node_size_scale_mode="diameter"
|
| 1279 |
+
)
|
| 1280 |
+
bar_df = load_bar_data(period['key'])
|
| 1281 |
+
bar_fig = make_figure(bar_df, period['key'], sort_by)
|
| 1282 |
+
return main_title, fig, bar_title, bar_fig
|
| 1283 |
+
|
| 1284 |
+
# === Семантическая карта ===
|
| 1285 |
+
@app.callback(
|
| 1286 |
+
Output('science-map-title', 'children'),
|
| 1287 |
+
Input('period-dropdown', 'value')
|
| 1288 |
+
)
|
| 1289 |
+
def update_science_map_title(period_key):
|
| 1290 |
+
period = next((p for p in PERIODS if p['key'] == period_key), PERIODS[0])
|
| 1291 |
+
period_years = period["label"]
|
| 1292 |
+
return f"Семантическая карта ({period_years})"
|
| 1293 |
+
|
| 1294 |
+
@app.callback(
|
| 1295 |
+
Output('science-map-plot', 'figure'),
|
| 1296 |
+
[Input('period-dropdown', 'value'),
|
| 1297 |
+
Input('size-dropdown', 'value'),
|
| 1298 |
+
Input('color-dropdown', 'value')]
|
| 1299 |
+
)
|
| 1300 |
+
def update_science_map(period_key, size_col, color_col):
|
| 1301 |
+
period = next((p for p in PERIODS if p['key'] == period_key), PERIODS[0])
|
| 1302 |
+
period_label = period["label"]
|
| 1303 |
+
df = load_science_map_sheet(period_label)
|
| 1304 |
+
df[size_col] = pd.to_numeric(df[size_col], errors='coerce')
|
| 1305 |
+
df['pub_title_short'] = df['pub_title'].apply(lambda s: shorten_text(s, MAX_LEN_HOVER))
|
| 1306 |
+
df['pub_authors_short'] = df['pub_authors'].apply(lambda s: shorten_text(s, MAX_LEN_HOVER))
|
| 1307 |
+
# ВАЖНО: Все cluster_id к строкам!
|
| 1308 |
+
df['author_cluster_id'] = df['author_cluster_id'].astype(str)
|
| 1309 |
+
df['semantic_cluster_id'] = df['semantic_cluster_id'].astype(str)
|
| 1310 |
+
cluster_ids = cluster_sorter(df[color_col].unique())
|
| 1311 |
+
# Готовим свою цветовую карту:
|
| 1312 |
+
palette = px.colors.qualitative.Alphabet if len(cluster_ids) <= 20 else px.colors.qualitative.Light24
|
| 1313 |
+
color_discrete_map = {k: palette[i % len(palette)] for i, k in enumerate(cluster_ids)}
|
| 1314 |
+
|
| 1315 |
+
custom_data = [
|
| 1316 |
+
'pub_id', 'pub_title_short', 'author_cluster_id', 'semantic_cluster_id',
|
| 1317 |
+
'pub_source', 'year', 'pub_authors_short', 'org_value', 'value', 'umap_x', 'umap_y'
|
| 1318 |
+
]
|
| 1319 |
+
fig = px.scatter(
|
| 1320 |
+
df,
|
| 1321 |
+
x='umap_x',
|
| 1322 |
+
y='umap_y',
|
| 1323 |
+
color=color_col,
|
| 1324 |
+
size=size_col,
|
| 1325 |
+
hover_data=[],
|
| 1326 |
+
custom_data=custom_data,
|
| 1327 |
+
template="plotly_white",
|
| 1328 |
+
height=850,
|
| 1329 |
+
category_orders={color_col: cluster_ids},
|
| 1330 |
+
color_discrete_map=color_discrete_map
|
| 1331 |
+
)
|
| 1332 |
+
hovertemplate = (
|
| 1333 |
+
"<b>%{customdata[1]}</b><br>"
|
| 1334 |
+
"Авторы: %{customdata[6]}<br>"
|
| 1335 |
+
"Источник: %{customdata[4]}<br>"
|
| 1336 |
+
"Год: %{customdata[5]}<br>"
|
| 1337 |
+
"ID публикации: %{customdata[0]}<br>"
|
| 1338 |
+
"Авторский кластер: %{customdata[2]}<br>"
|
| 1339 |
+
"Семантический кластер: %{customdata[3]}<br>"
|
| 1340 |
+
"Общая продуктивность: %{customdata[8]}<br>"
|
| 1341 |
+
"Вклад организации: %{customdata[7]}<br>"
|
| 1342 |
+
"Координаты: (%{customdata[9]}, %{customdata[10]})<br>"
|
| 1343 |
+
"<extra></extra>"
|
| 1344 |
+
)
|
| 1345 |
+
fig.update_traces(
|
| 1346 |
+
hovertemplate=hovertemplate,
|
| 1347 |
+
marker=dict(opacity=0.5, line=dict(width=1), sizemin=7),
|
| 1348 |
+
selector=dict(mode='markers')
|
| 1349 |
+
)
|
| 1350 |
+
fig.update_layout(
|
| 1351 |
+
hoverlabel=dict(font_size=10, font_family="Arial"),
|
| 1352 |
+
legend_title_text="",
|
| 1353 |
+
xaxis_title="X",
|
| 1354 |
+
yaxis_title="Y",
|
| 1355 |
+
legend=dict(
|
| 1356 |
+
orientation="h", yanchor="bottom", y=-0.8, xanchor="center", x=0.5,
|
| 1357 |
+
# Можно добавить ещё стилей, если надо
|
| 1358 |
+
),
|
| 1359 |
+
margin=dict(l=40, r=40, t=60, b=40),
|
| 1360 |
+
)
|
| 1361 |
+
return fig
|
| 1362 |
+
|
| 1363 |
+
|
| 1364 |
+
@app.callback(
|
| 1365 |
+
[Output('detail-title', 'children'),
|
| 1366 |
+
Output('detail-table', 'children')],
|
| 1367 |
+
[Input('science-map-plot', 'clickData'),
|
| 1368 |
+
Input('period-dropdown', 'value')]
|
| 1369 |
+
)
|
| 1370 |
+
def show_details(clickData, period_key):
|
| 1371 |
+
# Безопасный выбор периода
|
| 1372 |
+
period = next((p for p in PERIODS if p['key'] == period_key), None)
|
| 1373 |
+
if not period:
|
| 1374 |
+
return html.Div(
|
| 1375 |
+
"Ошибка: некорректные параметры периода! Проверьте PERIODS.",
|
| 1376 |
+
style={
|
| 1377 |
+
'fontFamily': 'Arial, sans-serif',
|
| 1378 |
+
'fontSize': '13px',
|
| 1379 |
+
'color': '#c00',
|
| 1380 |
+
'padding': '12px 0',
|
| 1381 |
+
'textAlign': 'center'
|
| 1382 |
+
}
|
| 1383 |
+
), ""
|
| 1384 |
+
|
| 1385 |
+
if clickData is None:
|
| 1386 |
+
return html.Div(
|
| 1387 |
+
"Кликните по точке для подробностей.",
|
| 1388 |
+
style={
|
| 1389 |
+
'fontFamily': 'Arial, sans-serif',
|
| 1390 |
+
'fontSize': '13px',
|
| 1391 |
+
'color': '#888',
|
| 1392 |
+
'padding': '12px 0',
|
| 1393 |
+
'textAlign': 'center'
|
| 1394 |
+
}
|
| 1395 |
+
), ""
|
| 1396 |
+
|
| 1397 |
+
pub_id = clickData['points'][0]['customdata'][0]
|
| 1398 |
+
|
| 1399 |
+
# Загружаем данные для выбранного периода
|
| 1400 |
+
df = load_science_map_sheet(period['label'])
|
| 1401 |
+
# Проверка — есть ли такая публикация?
|
| 1402 |
+
df_row = df[df['pub_id'] == pub_id]
|
| 1403 |
+
if df_row.empty:
|
| 1404 |
+
return html.Div(
|
| 1405 |
+
f"Публикация с pub_id={pub_id} не найдена в данных за период!",
|
| 1406 |
+
style={
|
| 1407 |
+
'fontFamily': 'Arial, sans-serif',
|
| 1408 |
+
'fontSize': '13px',
|
| 1409 |
+
'color': '#c00',
|
| 1410 |
+
'padding': '12px 0',
|
| 1411 |
+
'textAlign': 'center'
|
| 1412 |
+
}
|
| 1413 |
+
), ""
|
| 1414 |
+
row = df_row.iloc[0]
|
| 1415 |
+
|
| 1416 |
+
# --- Дальше оригинальный код по формированию detail-title и detail-table ---
|
| 1417 |
+
title = html.Div([
|
| 1418 |
+
html.Div(row['pub_title'], style={'fontWeight': 'bold', 'fontSize': '12px', 'marginBottom': '3px'}),
|
| 1419 |
+
html.Div([
|
| 1420 |
+
f"ID публикации: {row['pub_id']}", html.Br(),
|
| 1421 |
+
f"Авторский кластер: {row['author_cluster_id']}", html.Br(),
|
| 1422 |
+
f"Семантический кластер: {row['semantic_cluster_id']}", html.Br(),
|
| 1423 |
+
f"Источник: {row['pub_source']}", html.Br(),
|
| 1424 |
+
f"Год: {row['year']}", html.Br(),
|
| 1425 |
+
], style={'fontSize': '10px', 'color': '#555'}),
|
| 1426 |
+
], style={'marginBottom': '5px'})
|
| 1427 |
+
|
| 1428 |
+
abs_text = None
|
| 1429 |
+
sum_en = None
|
| 1430 |
+
sum_ru = None
|
| 1431 |
+
try:
|
| 1432 |
+
content_row = pub_content_df[pub_content_df['pub_id'] == pub_id]
|
| 1433 |
+
if not content_row.empty:
|
| 1434 |
+
abs_text = content_row.iloc[0]['abstract']
|
| 1435 |
+
sum_en = content_row.iloc[0]['summary_en']
|
| 1436 |
+
sum_ru = content_row.iloc[0]['summary_ru']
|
| 1437 |
+
except Exception:
|
| 1438 |
+
abs_text = sum_en = sum_ru = ""
|
| 1439 |
+
|
| 1440 |
+
author_line = row['pub_authors']
|
| 1441 |
+
authors_block = html.Div([
|
| 1442 |
+
html.Div("Авторы:", style={
|
| 1443 |
+
'fontWeight': 'bold',
|
| 1444 |
+
'fontSize': '12px',
|
| 1445 |
+
'marginTop': '8px',
|
| 1446 |
+
'marginBottom': '2px'
|
| 1447 |
+
}),
|
| 1448 |
+
html.Div(
|
| 1449 |
+
author_line,
|
| 1450 |
+
style={
|
| 1451 |
+
'fontSize': '10px',
|
| 1452 |
+
'color': '#222',
|
| 1453 |
+
'background': '#f8f8f8',
|
| 1454 |
+
'borderRadius': '8px',
|
| 1455 |
+
'padding': '8px 10px',
|
| 1456 |
+
'marginBottom': '5px',
|
| 1457 |
+
'maxHeight': '70px',
|
| 1458 |
+
'overflowY': 'auto'
|
| 1459 |
+
}
|
| 1460 |
+
),
|
| 1461 |
+
])
|
| 1462 |
+
|
| 1463 |
+
abstract_block = None
|
| 1464 |
+
if abs_text and isinstance(abs_text, str) and abs_text.strip():
|
| 1465 |
+
abstract_block = html.Div([
|
| 1466 |
+
html.Div("Аннотация:", style={
|
| 1467 |
+
'fontWeight': 'bold',
|
| 1468 |
+
'fontSize': '12px',
|
| 1469 |
+
'marginTop': '8px',
|
| 1470 |
+
'marginBottom': '2px'
|
| 1471 |
+
}),
|
| 1472 |
+
html.Div(abs_text, style={
|
| 1473 |
+
'fontSize': '10px',
|
| 1474 |
+
'color': '#222',
|
| 1475 |
+
'background': '#f8f8f8',
|
| 1476 |
+
'borderRadius': '8px',
|
| 1477 |
+
'padding': '8px 10px',
|
| 1478 |
+
'marginBottom': '5px',
|
| 1479 |
+
'maxHeight': '200px',
|
| 1480 |
+
'overflowY': 'auto'
|
| 1481 |
+
}),
|
| 1482 |
+
])
|
| 1483 |
+
|
| 1484 |
+
summary_en_block = None
|
| 1485 |
+
if sum_en and isinstance(sum_en, str) and sum_en.strip():
|
| 1486 |
+
summary_en_block = html.Div([
|
| 1487 |
+
html.Div("Текст вектора EN:", style={
|
| 1488 |
+
'fontWeight': 'bold',
|
| 1489 |
+
'fontSize': '12px',
|
| 1490 |
+
'marginTop': '10px',
|
| 1491 |
+
'marginBottom': '2px'
|
| 1492 |
+
}),
|
| 1493 |
+
html.Div(sum_en, style={
|
| 1494 |
+
'fontSize': '10px',
|
| 1495 |
+
'color': '#222',
|
| 1496 |
+
'background': '#f8f8f8',
|
| 1497 |
+
'borderRadius': '8px',
|
| 1498 |
+
'padding': '8px 10px',
|
| 1499 |
+
'marginBottom': '5px'
|
| 1500 |
+
}),
|
| 1501 |
+
])
|
| 1502 |
+
|
| 1503 |
+
summary_ru_block = None
|
| 1504 |
+
if sum_ru and isinstance(sum_ru, str) and sum_ru.strip():
|
| 1505 |
+
summary_ru_block = html.Div([
|
| 1506 |
+
html.Div("Текст вектора RU:", style={
|
| 1507 |
+
'fontWeight': 'bold',
|
| 1508 |
+
'fontSize': '12px',
|
| 1509 |
+
'marginTop': '10px',
|
| 1510 |
+
'marginBottom': '2px'
|
| 1511 |
+
}),
|
| 1512 |
+
html.Div(sum_ru, style={
|
| 1513 |
+
'fontSize': '10px',
|
| 1514 |
+
'color': '#222',
|
| 1515 |
+
'background': '#f4f4ff',
|
| 1516 |
+
'borderRadius': '8px',
|
| 1517 |
+
'padding': '8px 10px',
|
| 1518 |
+
'marginBottom': '5px'
|
| 1519 |
+
}),
|
| 1520 |
+
])
|
| 1521 |
+
|
| 1522 |
+
v = float(row['value']) if not pd.isnull(row['value']) else 0
|
| 1523 |
+
ov = float(row['org_value']) if not pd.isnull(row['org_value']) else 0
|
| 1524 |
+
if ov > v:
|
| 1525 |
+
ov = v
|
| 1526 |
+
other_value = max(v - ov, 0)
|
| 1527 |
+
pie_fig = go.Figure(go.Pie(
|
| 1528 |
+
labels=['Организация', 'Остальные'],
|
| 1529 |
+
values=[ov, other_value],
|
| 1530 |
+
hole=0.5,
|
| 1531 |
+
domain=dict(x=[0.2, 0.8], y=[0.2, 0.8])
|
| 1532 |
+
))
|
| 1533 |
+
pie_fig.update_traces(
|
| 1534 |
+
textinfo='percent',
|
| 1535 |
+
textfont_size=11,
|
| 1536 |
+
marker=dict(line=dict(color='#fff', width=1))
|
| 1537 |
+
)
|
| 1538 |
+
pie_fig.update_layout(
|
| 1539 |
+
showlegend=False,
|
| 1540 |
+
width=250, height=250,
|
| 1541 |
+
margin=dict(l=0, r=0, t=0, b=0),
|
| 1542 |
+
paper_bgcolor='#fafbfc'
|
| 1543 |
+
)
|
| 1544 |
+
|
| 1545 |
+
detail_items = []
|
| 1546 |
+
detail_items.append(authors_block)
|
| 1547 |
+
if abstract_block:
|
| 1548 |
+
detail_items.append(abstract_block)
|
| 1549 |
+
if SHOW_SUMMARY_EN and summary_en_block:
|
| 1550 |
+
detail_items.append(summary_en_block)
|
| 1551 |
+
if SHOW_SUMMARY_RU and summary_ru_block:
|
| 1552 |
+
detail_items.append(summary_ru_block)
|
| 1553 |
+
detail_items.extend([
|
| 1554 |
+
html.Div("Вклад в продуктивность:", style={
|
| 1555 |
+
'fontWeight': 'bold', 'fontSize': '12px', 'marginTop': '8px', 'marginBottom': '2px'
|
| 1556 |
+
}),
|
| 1557 |
+
dcc.Graph(
|
| 1558 |
+
figure=pie_fig,
|
| 1559 |
+
style={'height': '200px', 'width': '100%'},
|
| 1560 |
+
config={'displayModeBar': False}
|
| 1561 |
+
)
|
| 1562 |
+
])
|
| 1563 |
+
detail_html = html.Div(detail_items, style={'fontSize': '10px'})
|
| 1564 |
+
return title, detail_html
|
| 1565 |
+
|
| 1566 |
+
|
| 1567 |
+
|
| 1568 |
+
# === Download отчёт ===
|
| 1569 |
+
@app.callback(
|
| 1570 |
+
Output("download-report", "data"),
|
| 1571 |
+
Input("download-report-btn", "n_clicks"),
|
| 1572 |
+
prevent_initial_call=True,
|
| 1573 |
+
)
|
| 1574 |
+
def download_pdf(n_clicks):
|
| 1575 |
+
if not n_clicks:
|
| 1576 |
+
return dash.no_update
|
| 1577 |
+
if os.path.exists(PDF_PATH):
|
| 1578 |
+
with open(PDF_PATH, "rb") as f:
|
| 1579 |
+
return dcc.send_bytes(f.read(), "report.pdf")
|
| 1580 |
+
else:
|
| 1581 |
+
return dcc.send_string("В данной версии генерация отчетов отключена. Обратитесь к разработчику.", "report.txt")
|
| 1582 |
+
|
| 1583 |
+
# === Запуск ===
|
| 1584 |
+
if __name__ == '__main__':
|
| 1585 |
+
app.run(debug=False, host="0.0.0.0", port=8051)
|