diff --git a/src/main.ipynb b/src/main.ipynb index e7ab889..4696e52 100644 --- a/src/main.ipynb +++ b/src/main.ipynb @@ -45,7 +45,27 @@ "execution_count": 3, "id": "9fefb03b-d625-4db1-a59c-cd39dac90866", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Removed: ../output_data/key_value_type.csv\n", + "Removed: ../output_data/key_country.csv\n", + "Removed: ../output_data/key_jmp_name.csv\n", + "Removed: ../output_data/table_graph_ifs.csv\n", + "Removed: ../output_data/key_indicator.csv\n", + "Removed: ../output_data/key_jmp_category.csv\n", + "Removed: ../output_data/table_jmp.csv\n", + "Removed: ../output_data/table_ifs.csv\n", + "Removed: ../output_data/table_ifs_progress_rates.csv\n", + "Removed: ../output_data/key_value_name.csv\n", + "Removed: ../output_data/key_unit.csv\n", + "Removed: ../output_data/key_actual_commitment.csv\n", + "Removed: ../output_data/key_commitment.csv\n" + ] + } + ], "source": [ "csv_files = glob.glob(os.path.join(OUTPUT_DIR, '*.csv'))\n", "for file in csv_files:\n", @@ -538,14 +558,25 @@ "source": [ "def get_alb_value(x, df):\n", " if x[\"2nd_dimension\"] == \"Basic\":\n", - " additional_value = df[\n", - " (df[\"indicator\"] == x[\"indicator\"]) & \n", - " (df[\"year\"] == x[\"year\"]) & \n", - " (df[\"country\"] == x[\"country\"]) &\n", - " (df[\"commitment\"] == x[\"commitment\"]) &\n", - " (df[\"value_name\"] == x[\"value_name\"]) &\n", - " (df[\"2nd_dimension\"] == \"SafelyManaged\")\n", - " ]\n", + " if x[\"value_name\"] == \"Base\":\n", + " additional_value = df[\n", + " (df[\"indicator\"] == x[\"indicator\"]) & \n", + " (df[\"year\"] == x[\"year\"]) & \n", + " (df[\"country\"] == x[\"country\"]) &\n", + " (df[\"commitment\"] == x[\"commitment\"]) &\n", + " (df[\"value_name\"] == x[\"value_name\"]) &\n", + " (df[\"2nd_dimension\"] == \"SafelyManaged\")\n", + " ]\n", + " else:\n", + " additional_value = df[\n", + " (df[\"indicator\"] == x[\"indicator\"]) & \n", + " (df[\"year\"] == x[\"year\"]) & \n", + " (df[\"country\"] == x[\"country\"]) &\n", + " (df[\"jmp_category\"] == x[\"jmp_category\"]) &\n", + " (df[\"commitment\"] == x[\"commitment\"]) &\n", + " (df[\"value_name\"] == x[\"value_name\"]) &\n", + " (df[\"2nd_dimension\"] == \"SafelyManaged\")\n", + " ]\n", " if not additional_value.empty:\n", " return x[\"value\"] + additional_value[\"value\"].iloc[0]\n", " return x[\"value\"]" @@ -644,11 +675,6 @@ " df_final['jmp_category'] = df_final.apply(base_jmp_category, axis=1)\n", " df_final['jmp_category'] = df_final['jmp_category'].replace({\"BS\": \"ALB\"})\n", " \n", - " # Remove ALB From SafelyManaged\n", - " df_final['remove'] = df_final.apply(remove_unmatches_jmp_category, axis=1) \n", - " df_final = df_final[df_final['remove'] == False].reset_index(drop=True)\n", - " # End Remove\n", - " \n", " df_final['commitment'] = df_final.apply(modify_commitment_name, axis=1)\n", " # df_final.to_csv(\"testing-1.csv\",index=False)\n", " # Add Value for ALB\n", @@ -659,6 +685,11 @@ " # print(n)\n", " df_final['value'] = df_final.apply(lambda x: get_alb_value(x, df_final), axis=1)\n", "\n", + " # Remove ALB From SafelyManaged\n", + " df_final['remove'] = df_final.apply(remove_unmatches_jmp_category, axis=1) \n", + " df_final = df_final[df_final['remove'] == False].reset_index(drop=True)\n", + " # End Remove\n", + "\n", " # Add initial value column\n", " df_final['initial_value'] = np.nan\n", " df_final['base_value'] = np.nan\n", @@ -1950,7 +1981,7 @@ " \n", " 36383\n", " 2050\n", - " 14.482\n", + " 9.581\n", " 4.591\n", " 0.90\n", " NaN\n", @@ -2003,26 +2034,26 @@ "" ], "text/plain": [ - " year value base_value initial_value 2030 2050 remove \\\n", - "36381 2050 7.761 8.036 NaN NaN NaN False \n", - "36382 2050 16.6 NaN 5.53 NaN NaN False \n", - "36383 2050 14.482 4.591 0.90 NaN NaN False \n", - "36384 2050 7.209 8.036 NaN NaN NaN False \n", - "36385 2050 0.143 0.178 NaN NaN NaN False \n", + " year value base_value initial_value 2030 2050 remove jmp_name_id \\\n", + "36381 2050 7.761 8.036 NaN NaN NaN False 3 \n", + "36382 2050 16.6 NaN 5.53 NaN NaN False 1 \n", + "36383 2050 9.581 4.591 0.90 NaN NaN False 2 \n", + "36384 2050 7.209 8.036 NaN NaN NaN False 1 \n", + "36385 2050 0.143 0.178 NaN NaN NaN False 3 \n", "\n", - " jmp_name_id indicator_id unit_id value_name_id jmp_category_id \\\n", - "36381 3 5 4 7 1 \n", - "36382 1 12 5 1 2 \n", - "36383 2 6 5 2 1 \n", - "36384 1 5 4 6 2 \n", - "36385 3 4 4 7 2 \n", + " indicator_id unit_id value_name_id jmp_category_id commitment_id \\\n", + "36381 5 4 7 1 1 \n", + "36382 12 5 1 2 5 \n", + "36383 6 5 2 1 7 \n", + "36384 5 4 6 2 4 \n", + "36385 4 4 7 2 4 \n", "\n", - " commitment_id country_id \n", - "36381 1 22 \n", - "36382 5 15 \n", - "36383 7 10 \n", - "36384 4 22 \n", - "36385 4 23 " + " country_id \n", + "36381 22 \n", + "36382 15 \n", + "36383 10 \n", + "36384 22 \n", + "36385 23 " ] }, "execution_count": 45, diff --git a/tests/ifs-testing.csv b/tests/ifs-testing.csv index 8ec9e8f..ba9f712 100644 --- a/tests/ifs-testing.csv +++ b/tests/ifs-testing.csv @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:911c1dac85d73d48524bc7ef70f69b2c338edb289cee55fd7f7e80d69f5d275f -size 3405277 +oid sha256:9940b1c73d18316dba0f962d2fe80d9a57244b2e134bde98071a7857e705084f +size 3400107