Skip to content

Add baseline disaggregation code #561

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
handichan wants to merge 1 commit into
base: 518-add-disagg-code-and-tests-for-ak-hi
Choose a base branch
from
Open

Add baseline disaggregation code #561

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added scout/supporting_data/base_disagg/._2024_Convert_All.ipynb
View file
Open in desktop
Binary file not shown.
Binary file added scout/supporting_data/base_disagg/._test01_factors_differences.ipynb
View file
Open in desktop
Binary file not shown.
Binary file added scout/supporting_data/base_disagg/._test03_Validate_RECS_SEDS.ipynb
View file
Open in desktop
Binary file not shown.
Binary file added scout/supporting_data/base_disagg/._test04_nan_compare.ipynb
View file
Open in desktop
Binary file not shown.
1,896 changes: 1,896 additions & 0 deletions scout/supporting_data/base_disagg/2024_Convert_All.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

3,143 changes: 3,143 additions & 0 deletions scout/supporting_data/base_disagg/scout_geography.csv
View file
Open in desktop

Large diffs are not rendered by default.

230 changes: 230 additions & 0 deletions scout/supporting_data/base_disagg/test01_factors_differences.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,230 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "b5155e57-6bd6-46ed-9eee-d397c387b5e9",
"metadata": {},
"source": [
"### FIND DIFFERENCE BETWEEN 2024 and 2023 FACTORS"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cb0bd8b5-53a7-4ddd-b842-c634d8ec666c",
"metadata": {},
"outputs": [],
"source": [
"## Absolute difference\n",
"import pandas as pd\n",
"\n",
"filedir = \"./output/\"\n",
"# filename = \"Com_Cdiv_EMM_amy2018.csv\"\n",
"\n",
"\n",
"filenames = [\"Com_Cdiv_State_amy2018.csv\", \"Com_Cdiv_EMM_amy2018.csv\",\n",
" \"Res_Cdiv_EMM_amy2018.csv\", \"Res_Cdiv_State_amy2018.csv\"]\n",
" \n",
"for filename in filenames:\n",
" file1_path = f\"{filedir}2023/{filename}\"\n",
" file2_path = f\"{filedir}2024_end_use/{filename}\"\n",
" df1 = pd.read_csv(file1_path)\n",
" df2 = pd.read_csv(file2_path)\n",
"\n",
" sorted_df1 = df1.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" sorted_df2 = df2.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" # if filename ==\"Com_Cdiv_State_amy2018.csv\":\n",
" # print(filename)\n",
" # print(sorted_df1.iloc[0:9])\n",
" # print(sorted_df2.iloc[0:9])\n",
" \n",
" common_columns = sorted_df1.columns.intersection(sorted_df2.columns)\n",
" df1_common = sorted_df1[common_columns]\n",
" df2_common = sorted_df2[common_columns]\n",
" df1_numeric = df1_common.select_dtypes(include='number')\n",
" df2_numeric = df2_common.select_dtypes(include='number')\n",
" absolute_difference_df = df2_numeric.subtract(df1_numeric, fill_value=0)\n",
" absolute_difference_df_from_third_column = absolute_difference_df.iloc[:, 1:]\n",
" # percentage_difference_df = df1_numeric.subtract(df2_numeric, fill_value=0).abs().divide(df1_numeric, fill_value=1)\n",
" # percentage_difference_df_from_third_column = percentage_difference_df.iloc[:, 1:]\n",
"\n",
" shifted_absolute_difference_df = pd.concat([pd.DataFrame(index=df1_common.index, columns=[\"placeholder\"]), absolute_difference_df_from_third_column], axis=1)\n",
" df_with_inserted_columns = pd.concat([df1_common.iloc[:, :2], shifted_absolute_difference_df], axis=1)\n",
"\n",
" df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], absolute_difference_df_from_third_column], axis=1)\n",
" # df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], percentage_difference_df_from_third_column], axis=1)\n",
" \n",
" df_with_first_two_columns = df_with_first_two_columns.fillna(0)\n",
" output_path = f\"{filedir}pctdiff/absdiff_{filename}\"\n",
" df_with_first_two_columns.to_csv(output_path, index=False)\n",
" print(\"COMPLETE\")\n",
"\n",
"# tools.display_dataframe_to_user(name=\"Absolute Differences (Starting from Third Column)\", dataframe=absolute_difference_df_from_third_column)\n",
"# # Output path for reference\n",
"# output_path\n",
"\n",
"\n",
"\n",
"#### ResStock, number of homes; ComStock, square footage\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "85c03de3-d185-49ec-b27a-85e4bc62e91d",
"metadata": {},
"outputs": [],
"source": [
"## Percent difference\n",
"import pandas as pd\n",
"\n",
"filedir = \"./output/\"\n",
"# filename = \"Com_Cdiv_EMM_amy2018.csv\"\n",
"\n",
"\n",
"filenames = [\"Com_Cdiv_State_amy2018.csv\", \"Com_Cdiv_EMM_amy2018.csv\",\n",
" \"Res_Cdiv_EMM_amy2018.csv\", \"Res_Cdiv_State_amy2018.csv\"]\n",
" \n",
"for filename in filenames:\n",
" file1_path = f\"{filedir}2023/{filename}\"\n",
" file2_path = f\"{filedir}2024_end_use/{filename}\"\n",
" df1 = pd.read_csv(file1_path)\n",
" df2 = pd.read_csv(file2_path)\n",
"\n",
" sorted_df1 = df1.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" sorted_df2 = df2.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" # if filename ==\"Com_Cdiv_State_amy2018.csv\":\n",
" # print(filename)\n",
" # print(sorted_df1.iloc[0:9])\n",
" # print(sorted_df2.iloc[0:9])\n",
" \n",
" common_columns = sorted_df1.columns.intersection(sorted_df2.columns)\n",
" df1_common = sorted_df1[common_columns]\n",
" df2_common = sorted_df2[common_columns]\n",
" df1_numeric = df1_common.select_dtypes(include='number')\n",
" df2_numeric = df2_common.select_dtypes(include='number')\n",
" # absolute_difference_df = df1_numeric.subtract(df2_numeric, fill_value=0).abs()\n",
" # absolute_difference_df_from_third_column = absolute_difference_df.iloc[:, 1:]\n",
" percentage_difference_df = df2_numeric.subtract(df1_numeric, fill_value=0).divide(df1_numeric, fill_value=1)\n",
" percentage_difference_df_from_third_column = percentage_difference_df.iloc[:, 1:]\n",
"\n",
" # shifted_absolute_difference_df = pd.concat([pd.DataFrame(index=df1_common.index, columns=[\"placeholder\"]), absolute_difference_df_from_third_column], axis=1)\n",
" # df_with_inserted_columns = pd.concat([df1_common.iloc[:, :2], shifted_absolute_difference_df], axis=1)\n",
"\n",
" # df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], absolute_difference_df_from_third_column], axis=1)\n",
" df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], percentage_difference_df_from_third_column], axis=1)\n",
" \n",
" df_with_first_two_columns = df_with_first_two_columns.fillna(0)\n",
" output_path = f\"{filedir}pctdiff/pctdiff_{filename}\"\n",
" df_with_first_two_columns.to_csv(output_path, index=False)\n",
" print(\"COMPLETE\")\n",
"\n",
"# tools.display_dataframe_to_user(name=\"Absolute Differences (Starting from Third Column)\", dataframe=absolute_difference_df_from_third_column)\n",
"# # Output path for reference\n",
"# output_path\n",
"\n",
"\n",
"\n",
"#### ResStock, number of homes; ComStock, square footage\n"
]
},
{
"cell_type": "markdown",
"id": "3b3725cd-ba72-459f-a62a-599c7572cbad",
"metadata": {},
"source": [
"### End use and Stock"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "79cb7df7-1b26-470f-a32c-fa083fcbedf0",
"metadata": {},
"outputs": [],
"source": [
"## Percent difference\n",
"import pandas as pd\n",
"\n",
"filedir = \"./output/\"\n",
"# filename = \"Com_Cdiv_EMM_amy2018.csv\"\n",
"\n",
"\n",
"filenames = [\"Com_Cdiv_State_amy2018.csv\", \"Com_Cdiv_EMM_amy2018.csv\",\n",
" \"Res_Cdiv_EMM_amy2018.csv\", \"Res_Cdiv_State_amy2018.csv\"]\n",
" \n",
"for filename in filenames:\n",
" file_stock = filename.replace(\".csv\", \"_Stock.csv\")\n",
" file1_path = f\"{filedir}2024_end_use/{filename}\"\n",
" file2_path = f\"{filedir}2024_end_use/{file_stock}\"\n",
" df1 = pd.read_csv(file1_path)\n",
" df2 = pd.read_csv(file2_path)\n",
"\n",
" sorted_df1 = df1.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" sorted_df2 = df2.sort_values(by=[\"End use\", \"CDIV\"]).reset_index(drop=True)\n",
" # if filename ==\"Com_Cdiv_State_amy2018.csv\":\n",
" # print(filename)\n",
" # print(sorted_df1.iloc[0:9])\n",
" # print(sorted_df2.iloc[0:9])\n",
" \n",
" common_columns = sorted_df1.columns.intersection(sorted_df2.columns)\n",
" df1_common = sorted_df1[common_columns]\n",
" df2_common = sorted_df2[common_columns]\n",
" df1_numeric = df1_common.select_dtypes(include='number')\n",
" df2_numeric = df2_common.select_dtypes(include='number')\n",
" # absolute_difference_df = df1_numeric.subtract(df2_numeric, fill_value=0).abs()\n",
" # absolute_difference_df_from_third_column = absolute_difference_df.iloc[:, 1:]\n",
" percentage_difference_df = df2_numeric.subtract(df1_numeric, fill_value=0).divide(df1_numeric, fill_value=1)\n",
" percentage_difference_df_from_third_column = percentage_difference_df.iloc[:, 1:]\n",
"\n",
" # shifted_absolute_difference_df = pd.concat([pd.DataFrame(index=df1_common.index, columns=[\"placeholder\"]), absolute_difference_df_from_third_column], axis=1)\n",
" # df_with_inserted_columns = pd.concat([df1_common.iloc[:, :2], shifted_absolute_difference_df], axis=1)\n",
"\n",
" # df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], absolute_difference_df_from_third_column], axis=1)\n",
" df_with_first_two_columns = pd.concat([df1_common.iloc[:, :2], percentage_difference_df_from_third_column], axis=1)\n",
" \n",
" df_with_first_two_columns = df_with_first_two_columns.fillna(0)\n",
" output_path = f\"{filedir}pctdiff/pctdiff_stock_{filename}\"\n",
" df_with_first_two_columns.to_csv(output_path, index=False)\n",
" print(\"COMPLETE\")\n",
"\n",
"# tools.display_dataframe_to_user(name=\"Absolute Differences (Starting from Third Column)\", dataframe=absolute_difference_df_from_third_column)\n",
"# # Output path for reference\n",
"# output_path\n",
"\n",
"\n",
"\n",
"#### ResStock, number of homes; ComStock, square footage\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b14d3f76-0dc4-4a9d-be0b-375d8e2e053b",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading