Skip to content

Commit

Permalink
iccs_notebook for data exploration
Browse files Browse the repository at this point in the history
  • Loading branch information
@inikokali
inikokali committed Jul 8, 2024
1 parent 45c7420 commit 6a7c765
Showing 1 changed file with 244 additions and 0 deletions.
244 changes: 244 additions & 0 deletions src/notebooks/reader.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,244 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "24860b03-131e-488d-a5d1-6f4b44521a13",
"metadata": {},
"source": [
"## General Description\n",
"\n",
"This script reads data from a VTK EnSight Gold binary file and processes it to extract information about solar shading coefficients and the geometry of cells over a series of timesteps. The key steps include:\n",
"\n",
"1. **Setting up the Reader**: The script initializes a VTK reader for the EnSight Gold binary file format and configures it to read all variables from a specified case file.\n",
"\n",
"2. **Processing Data for Each Timestep**: For each timestep, the script updates the reader with the current time value, retrieves cell data including solar shading coefficients, and extracts the geometric points defining each cell. This data is combined and converted into a pandas DataFrame with appropriate column names.\n",
"\n",
"3. **Calculating the Area of Triangles**: A function calculates the area of a triangle given its vertices. This function is used to compute the area for each triangle (cell) in the DataFrame, and these areas are added as a new column in the DataFrame.\n",
"\n",
"4. **Saving the Data**: The resulting DataFrame is saved to a CSV file for further analysis or use.\n",
"\n",
"This script provides a comprehensive framework for reading, processing, and analyzing time-dependent geometric and scalar data from a VTK EnSight Gold binary file.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "61ee8919-195b-4d1f-8ff1-a94603596143",
"metadata": {},
"outputs": [],
"source": [
"import vtk\n",
"\n",
"# Setup the reader\n",
"# We suppose that the necessarty files are in the same directory as the notebook\n",
"case_file = \"strasbourg_sm_lod1/strasbourg_sm_lod1/City_Energy_Modeling.case\"\n",
"# Setup the reader\n",
"reader = vtk.vtkEnSightGoldBinaryReader()\n",
"reader.SetCaseFileName(case_file)\n",
"reader.ReadAllVariablesOn() # Ensure all variables are read\n",
"reader.Update()\n",
"\n",
"# Retrieve the output\n",
"output = reader.GetOutput()\n",
"timeset=reader.GetTimeSets()\n",
"time=timeset.GetItem(0)\n",
"timesteps=time.GetSize()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "96eede0d-c63e-4187-94e0-f473df853c42",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of timesteps: 731\n",
"Number of cells: 212692\n",
"Number of scalar points?: 212692\n"
]
}
],
"source": [
"print(\"Number of timesteps: \", timesteps)\n",
"print(\"Number of cells: \", reader.GetOutput().GetBlock(0).GetNumberOfCells())\n",
"print(\"Number of scalar points?: \", reader.GetOutput().GetBlock(0).GetCellData().GetArray(\"solar_shading_coeff\").GetNumberOfTuples())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a6e05806-9a22-488a-902d-495e19899620",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"212692\n"
]
}
],
"source": [
"print(output.GetNumberOfCells())"
]
},
{
"cell_type": "markdown",
"id": "2b0e67e6-39ca-4eed-954d-2e210306a996",
"metadata": {},
"source": [
"## Panda Dataframes"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "db60d12d-b71a-41e7-a11f-14bfafe3d00a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" timestep x_1 y_1 z_1 x_2 y_2 z_2 \\\n",
"0 0 -539.268982 600.049988 0.0 -538.495972 599.625000 0.0 \n",
"1 0 -541.656982 611.940979 0.0 -527.434998 605.570984 0.0 \n",
"2 0 -527.434998 605.570984 0.0 -538.495972 599.625000 0.0 \n",
"3 0 -487.437988 635.723999 0.0 -490.282013 625.955994 0.0 \n",
"4 0 -488.596985 642.520020 0.0 -487.437988 635.723999 0.0 \n",
"\n",
" x_3 y_3 z_3 scalar area \n",
"0 -538.987976 599.625000 0.0 0.0 0.104548 \n",
"1 -539.268982 600.049988 0.0 0.0 76.950973 \n",
"2 -539.268982 600.049988 0.0 0.0 4.648543 \n",
"3 -518.830994 625.955994 0.0 0.0 139.433298 \n",
"4 -518.830994 625.955994 0.0 0.0 112.334297 \n"
]
}
],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"# Initialize an empty list to accumulate the arrays\n",
"data = []\n",
"\n",
"for t in range(timesteps):\n",
" reader.SetTimeValue(time.GetValue(t))\n",
" reader.Update()\n",
" output = reader.GetOutput().GetBlock(0)\n",
" cell_data = output.GetCellData()\n",
" sc = cell_data.GetArray(\"solar_shading_coeff\")\n",
"\n",
"\n",
" for i in range(output.GetNumberOfCells()):\n",
" cell = output.GetCell(i)\n",
" pts = cell.GetPoints()\n",
" scalar = sc.GetTuple(i)\n",
" np_pts = np.array([pts.GetPoint(j) for j in range(pts.GetNumberOfPoints())])\n",
" \n",
" flattened_pts = np_pts.flatten()\n",
" combined_data = np.append(flattened_pts, scalar[0])\n",
" \n",
" # Append the timestep and combined data to the list\n",
" data.append([t] + combined_data.tolist())\n",
" # data.append(np.insert(combined_data, 0, t))\n",
"\n",
"# Create column names for the DataFrame\n",
"columns = ['timestep'] + ['x_1'] + ['y_1'] + ['z_1'] + ['x_2'] + ['y_2'] + ['z_2'] + ['x_3'] + ['y_3'] + ['z_3'] + ['scalar']\n",
"\n",
"# Convert the list to a DataFrame\n",
"df = pd.DataFrame(data, columns=columns)\n",
"\n",
"# Function to calculate the area of a triangle given its vertices\n",
"def calculate_triangle_area(p1, p2, p3):\n",
" # Calculate the vectors for two sides of the triangle\n",
" v1 = p2 - p1\n",
" v2 = p3 - p1\n",
" # Calculate the cross product of the vectors\n",
" cross_product = np.cross(v1, v2)\n",
" # Calculate the area of the triangle (0.5 * magnitude of the cross product)\n",
" area = 0.5 * np.linalg.norm(cross_product)\n",
" return area\n",
"\n",
"# Calculate the area for each triangle and add it as a new column\n",
"areas = []\n",
"for index, row in df.iterrows():\n",
" p1 = np.array([row['x_1'], row['y_1'], row['z_1']])\n",
" p2 = np.array([row['x_2'], row['y_2'], row['z_2']])\n",
" p3 = np.array([row['x_3'], row['y_3'], row['z_3']])\n",
" area = calculate_triangle_area(p1, p2, p3)\n",
" areas.append(area)\n",
"\n",
"df['area'] = areas\n",
"\n",
"# Print the resulting DataFrame\n",
"print(df.head())"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "2b590da1-99db-454c-acd3-b785e2c283b4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" timestep point_1 point_2 point_3 point_4 point_5 \\\n",
"5104603 23 725.992004 -1084.459961 0.0 725.992004 -1084.459961 \n",
"5104604 23 739.231018 -1185.939941 0.0 737.825989 -1185.089966 \n",
"5104605 23 737.825989 -1185.089966 0.0 737.825989 -1185.089966 \n",
"5104606 23 763.109985 -1150.270020 0.0 760.265015 -1155.369995 \n",
"5104607 23 760.265015 -1155.369995 0.0 760.265015 -1155.369995 \n",
"\n",
" point_6 point_7 point_8 point_9 scalar area \n",
"5104603 5.2 726.484009 -1079.369995 5.2 1.0 13.295592 \n",
"5104604 0.0 739.231018 -1185.939941 6.5 1.0 5.336898 \n",
"5104605 6.5 739.231018 -1185.939941 6.5 1.0 5.336898 \n",
"5104606 0.0 763.109985 -1150.270020 3.0 1.0 8.759744 \n",
"5104607 3.0 763.109985 -1150.270020 3.0 1.0 8.759744 \n"
]
}
],
"source": [
"print(df.tail())"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "7e470e53-0506-43a2-9d12-50deef85fbfa",
"metadata": {},
"outputs": [],
"source": [
"df.to_csv('initial_dataframe.csv', index=False)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

0 comments on commit 6a7c765

Please sign in to comment.