From 3e395922ef9697f31d3fa010923f6c6d10b45e55 Mon Sep 17 00:00:00 2001 From: Julia Suter Date: Tue, 28 Feb 2023 14:22:04 +0000 Subject: [PATCH] Notebook with completed outputs --- asf_core_data/analysis/process_new_data.ipynb | 338 +++--------------- 1 file changed, 40 insertions(+), 298 deletions(-) diff --git a/asf_core_data/analysis/process_new_data.ipynb b/asf_core_data/analysis/process_new_data.ipynb index d4a91bf..b9f6f13 100644 --- a/asf_core_data/analysis/process_new_data.ipynb +++ b/asf_core_data/analysis/process_new_data.ipynb @@ -18,14 +18,16 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2023-02-28 11:56:52,876 - botocore.credentials - INFO - Found credentials in shared credentials file: ~/.aws/credentials\n" + "The autoreload extension is already loaded. To reload it, use:\n", + " %reload_ext autoreload\n", + "2023-03-01 09:24:44,936 - botocore.credentials - INFO - Found credentials in shared credentials file: ~/.aws/credentials\n" ] } ], @@ -58,7 +60,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -102,38 +104,9 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Saving raw data to /Users/juliasuter/Documents/My_ASF_data/outputs/EPC/preprocessed_data/2022_Q3_complete/EPC_GB_raw.csv\n", - "\n" - ] - }, - { - "ename": "KeyboardInterrupt", - "evalue": "", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Process new batch of EPC data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m epc_full = preprocess_epc_data.load_and_preprocess_epc_data(\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mdata_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mLOCAL_DATA_DIR\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"newest\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubset\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'GB'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mreload_raw\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m )\n", - "\u001b[0;32m~/Documents/repositories/asf_core_data/asf_core_data/pipeline/preprocessing/preprocess_epc_data.py\u001b[0m in \u001b[0;36mload_and_preprocess_epc_data\u001b[0;34m(data_path, rel_data_path, subset, usecols, batch, n_samples, remove_duplicates, save_data, reload_raw)\u001b[0m\n\u001b[1;32m 252\u001b[0m )\n\u001b[1;32m 253\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 254\u001b[0;31m epc_df = preprocess_data(\n\u001b[0m\u001b[1;32m 255\u001b[0m \u001b[0mepc_df\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 256\u001b[0m \u001b[0mdata_path\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdata_path\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/Documents/repositories/asf_core_data/asf_core_data/pipeline/preprocessing/preprocess_epc_data.py\u001b[0m in \u001b[0;36mpreprocess_data\u001b[0;34m(df, remove_duplicates, data_path, subset, batch, save_data, verbose)\u001b[0m\n\u001b[1;32m 80\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 81\u001b[0m \u001b[0;31m# Save unaltered_version\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 82\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 83\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0mprocessing_steps\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36mto_csv\u001b[0;34m(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, decimal, errors, storage_options)\u001b[0m\n\u001b[1;32m 3549\u001b[0m )\n\u001b[1;32m 3550\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3551\u001b[0;31m return DataFrameRenderer(formatter).to_csv(\n\u001b[0m\u001b[1;32m 3552\u001b[0m \u001b[0mpath_or_buf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3553\u001b[0m \u001b[0mline_terminator\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mline_terminator\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/io/formats/format.py\u001b[0m in \u001b[0;36mto_csv\u001b[0;34m(self, path_or_buf, encoding, sep, columns, index_label, mode, compression, quoting, quotechar, line_terminator, chunksize, date_format, doublequote, escapechar, errors, storage_options)\u001b[0m\n\u001b[1;32m 1178\u001b[0m \u001b[0mformatter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfmt\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1179\u001b[0m )\n\u001b[0;32m-> 1180\u001b[0;31m \u001b[0mcsv_formatter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1181\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1182\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcreated_buffer\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/io/formats/csvs.py\u001b[0m in \u001b[0;36msave\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 259\u001b[0m )\n\u001b[1;32m 260\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 261\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 262\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 263\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_save\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/io/formats/csvs.py\u001b[0m in \u001b[0;36m_save\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 264\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_need_to_save_header\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 265\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save_header\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 266\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save_body\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 267\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 268\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_save_header\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/io/formats/csvs.py\u001b[0m in \u001b[0;36m_save_body\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 302\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mstart_i\u001b[0m \u001b[0;34m>=\u001b[0m \u001b[0mend_i\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 303\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 304\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_save_chunk\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart_i\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mend_i\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 305\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 306\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_save_chunk\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstart_i\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mend_i\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m~/opt/anaconda3/envs/asf_core_data/lib/python3.8/site-packages/pandas/io/formats/csvs.py\u001b[0m in \u001b[0;36m_save_chunk\u001b[0;34m(self, start_i, end_i)\u001b[0m\n\u001b[1;32m 313\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 314\u001b[0m \u001b[0mix\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_index\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mslicer\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_format_native_types\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_number_format\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 315\u001b[0;31m libwriters.write_csv_rows(\n\u001b[0m\u001b[1;32m 316\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 317\u001b[0m \u001b[0mix\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32mpandas/_libs/writers.pyx\u001b[0m in \u001b[0;36mpandas._libs.writers.write_csv_rows\u001b[0;34m()\u001b[0m\n", - "\u001b[0;31mKeyboardInterrupt\u001b[0m: " - ] - } - ], + "outputs": [], "source": [ "# Process new batch of EPC data\n", "epc_full = preprocess_epc_data.load_and_preprocess_epc_data(\n", @@ -290,16 +263,9 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": {}, "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "2023-02-28 02:11:48,413 - botocore.credentials - INFO - Found credentials in shared credentials file: ~/.aws/credentials\n" - ] - }, { "name": "stderr", "output_type": "stream", @@ -409,7 +375,7 @@ "(19047896, 64)" ] }, - "execution_count": 4, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } @@ -433,19 +399,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "metadata": {}, "outputs": [ { - "ename": "NameError", - "evalue": "name 'epc_with_MCS_dates' is not defined", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mepc_mcs_processed\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmerge_proc_datasets\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmerge_proc_epc_and_mcs_installations\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mepc_with_MCS_dates\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mepc_mcs_processed\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mNameError\u001b[0m: name 'epc_with_MCS_dates' is not defined" + "name": "stdout", + "output_type": "stream", + "text": [ + "EPC (19047896, 65)\n", + "MCS (168574, 13)\n", + "MCS (EPC matched) (139748, 13)\n", + "MCS (EPC unmatched) (28826, 13)\n", + "EPC and MCS merged (19082606, 75)\n" ] + }, + { + "data": { + "text/plain": [ + "(19082606, 75)" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ @@ -458,261 +434,21 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Get historical installer data (and finally merge it with the rest)" + "Get historical installer data (and finally merge it with the rest). This is just for demonstration, not as it would be handled in the final pipeline. Please refer to `merge_proc_datasets.py`" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "outputs/MCS/installers/mcs_historical_installers_20230207.csv\n" + "outputs/MCS/installers/mcs_historical_installers_20230207.csv\n", + "2023-03-01 09:25:14,272 - botocore.credentials - INFO - Found credentials in shared credentials file: ~/.aws/credentials\n" ] - }, - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
company_unique_idcompany_namemcs_certificate_numbercertification_bodyaddress_1address_2towncountypostcodelatitude...solar_pv_certifiedwind_turbine_certifiedsolar_thermal_certifiedbattery_storage_certifiedair_source_hp_certifiedground_water_source_hp_certifiedhot_water_hp_certifiedexhaust_air_hp_certifiedgas_absorbtion_hp_certifiedsolar_assisted_hp_certified
0t j galvin plumbing heating engineersT J Galvin Plumbing & Heating Engineers1283MCSBrandoak HouseStoneBerkeleyGloucestershireGL139LA51.652315...FalseFalseFalseFalseTrueTrueFalseFalseFalseFalse
1paragon systems scotlandParagon Systems (Scotland) Ltd1286MCSThe Office, Corbie CottageMaryculterAberdeenAberdeenshireAB125FT57.089012...FalseFalseFalseFalseTrueTrueFalseTrueFalseFalse
2carillion energy servicesCarillion Energy Services Limited1290MCSPartnership House, Regent Farm RoadGosforthNewcastle Upon TyneTyne and WearNE33AF55.010499...TrueFalseTrueFalseTrueTrueFalseTrueFalseFalse
3edwards ukEdwards UK Ltd t/a Nugenn1292MCSSuite 2, Cumbria HouseGillwilly RoadPenrithCumbriaCA119FF54.665127...FalseFalseFalseFalseTrueTrueFalseTrueFalseFalse
4jdk enterprisesJDK Enterprises Ltd t/a Solar Air UK1294NaN6 HilltopStanley RoadWhitstableKentCT54QE51.346942...FalseFalseTrueFalseTrueTrueFalseTrueFalseFalse
\n", - "

5 rows × 54 columns

\n", - "
" - ], - "text/plain": [ - " company_unique_id \\\n", - "0 t j galvin plumbing heating engineers \n", - "1 paragon systems scotland \n", - "2 carillion energy services \n", - "3 edwards uk \n", - "4 jdk enterprises \n", - "\n", - " company_name mcs_certificate_number \\\n", - "0 T J Galvin Plumbing & Heating Engineers 1283 \n", - "1 Paragon Systems (Scotland) Ltd 1286 \n", - "2 Carillion Energy Services Limited 1290 \n", - "3 Edwards UK Ltd t/a Nugenn 1292 \n", - "4 JDK Enterprises Ltd t/a Solar Air UK 1294 \n", - "\n", - " certification_body address_1 address_2 \\\n", - "0 MCS Brandoak House Stone \n", - "1 MCS The Office, Corbie Cottage Maryculter \n", - "2 MCS Partnership House, Regent Farm Road Gosforth \n", - "3 MCS Suite 2, Cumbria House Gillwilly Road \n", - "4 NaN 6 Hilltop Stanley Road \n", - "\n", - " town county postcode latitude ... \\\n", - "0 Berkeley Gloucestershire GL139LA 51.652315 ... \n", - "1 Aberdeen Aberdeenshire AB125FT 57.089012 ... \n", - "2 Newcastle Upon Tyne Tyne and Wear NE33AF 55.010499 ... \n", - "3 Penrith Cumbria CA119FF 54.665127 ... \n", - "4 Whitstable Kent CT54QE 51.346942 ... \n", - "\n", - " solar_pv_certified wind_turbine_certified solar_thermal_certified \\\n", - "0 False False False \n", - "1 False False False \n", - "2 True False True \n", - "3 False False False \n", - "4 False False True \n", - "\n", - " battery_storage_certified air_source_hp_certified \\\n", - "0 False True \n", - "1 False True \n", - "2 False True \n", - "3 False True \n", - "4 False True \n", - "\n", - " ground_water_source_hp_certified hot_water_hp_certified \\\n", - "0 True False \n", - "1 True False \n", - "2 True False \n", - "3 True False \n", - "4 True False \n", - "\n", - " exhaust_air_hp_certified gas_absorbtion_hp_certified \\\n", - "0 False False \n", - "1 True False \n", - "2 True False \n", - "3 True False \n", - "4 True False \n", - "\n", - " solar_assisted_hp_certified \n", - "0 False \n", - "1 False \n", - "2 False \n", - "3 False \n", - "4 False \n", - "\n", - "[5 rows x 54 columns]" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" } ], "source": [ @@ -724,9 +460,15 @@ "mcs_inst_data = data_getters.load_s3_data(\n", " base_config.BUCKET_NAME,\n", " newest_hist_inst_batch,\n", - ")\n", - "mcs_inst_data.head()" + ")" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": {