diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 22df950..94a8a3d 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -19,7 +19,7 @@ jobs: - name: Set up Python uses: actions/setup-python@v2 with: - python-version: '3.x' + python-version: '3.11' - name: Install dependencies run: | diff --git a/demo_final_contact_matrix.ipynb b/demo_final_contact_matrix.ipynb index f15f795..01e71b4 100644 --- a/demo_final_contact_matrix.ipynb +++ b/demo_final_contact_matrix.ipynb @@ -24,7 +24,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -49,10 +49,10 @@ " \n", " \n", " ID\n", + " date\n", " merch_category\n", " merch_postal_code\n", " transaction_type\n", - " date\n", " spendamt\n", " nb_transactions\n", " \n", @@ -61,80 +61,80 @@ " \n", " 0\n", " 1\n", - " Hospitals\n", - " 111921\n", - " ONLINE\n", " 2019-01-01\n", - " 80797.323317\n", - " 398\n", + " Grocery Stores/Supermarkets\n", + " 8700000\n", + " ONLINE\n", + " 11238.128450\n", + " 160\n", " \n", " \n", " 1\n", - " 2\n", - " Bars/Discotheques\n", - " 050025\n", - " OFFLINE\n", + " 1\n", " 2019-01-01\n", - " 5331.031100\n", - " 283\n", + " Grocery Stores/Supermarkets\n", + " 500034\n", + " ONLINE\n", + " 12848.165221\n", + " 183\n", " \n", " \n", " 2\n", " 2\n", - " Bars/Discotheques\n", - " 050032\n", - " OFFLINE\n", " 2019-01-01\n", - " 5180.722635\n", - " 268\n", + " Grocery Stores/Supermarkets\n", + " 110621\n", + " ONLINE\n", + " 12116.165569\n", + " 173\n", " \n", " \n", " 3\n", " 3\n", - " Drug Stores/Pharmacies\n", - " 050012\n", - " OFFLINE\n", " 2019-01-01\n", - " 5032.333763\n", - " 177\n", + " Hotels/Motels\n", + " 8900000\n", + " OFFLINE\n", + " 7745.998879\n", + " 38\n", " \n", " \n", " 4\n", - " 3\n", - " Drug Stores/Pharmacies\n", - " 050031\n", - " OFFLINE\n", + " 4\n", " 2019-01-01\n", - " 4899.182326\n", - " 150\n", + " Restaurants\n", + " 111941\n", + " OFFLINE\n", + " 6927.424754\n", + " 173\n", " \n", " \n", "\n", "" ], "text/plain": [ - " ID merch_category merch_postal_code transaction_type date \\\n", - "0 1 Hospitals 111921 ONLINE 2019-01-01 \n", - "1 2 Bars/Discotheques 050025 OFFLINE 2019-01-01 \n", - "2 2 Bars/Discotheques 050032 OFFLINE 2019-01-01 \n", - "3 3 Drug Stores/Pharmacies 050012 OFFLINE 2019-01-01 \n", - "4 3 Drug Stores/Pharmacies 050031 OFFLINE 2019-01-01 \n", + " ID date merch_category merch_postal_code \\\n", + "0 1 2019-01-01 Grocery Stores/Supermarkets 8700000 \n", + "1 1 2019-01-01 Grocery Stores/Supermarkets 500034 \n", + "2 2 2019-01-01 Grocery Stores/Supermarkets 110621 \n", + "3 3 2019-01-01 Hotels/Motels 8900000 \n", + "4 4 2019-01-01 Restaurants 111941 \n", "\n", - " spendamt nb_transactions \n", - "0 80797.323317 398 \n", - "1 5331.031100 283 \n", - "2 5180.722635 268 \n", - "3 5032.333763 177 \n", - "4 4899.182326 150 " + " transaction_type spendamt nb_transactions \n", + "0 ONLINE 11238.128450 160 \n", + "1 ONLINE 12848.165221 183 \n", + "2 ONLINE 12116.165569 173 \n", + "3 OFFLINE 7745.998879 38 \n", + "4 OFFLINE 6927.424754 173 " ] }, - "execution_count": 3, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "data = pd.read_csv(r\"C:\\Users\\Milan Anand Raj\\Desktop\\KNOWLEDGEEDGEAI\\PET\\final_data\\final_technical_data.csv\")\n", + "data = pd.read_csv(r'D:\\workspace\\PET\\technical_phase_data.csv')\n", "data.head()" ] }, @@ -147,7 +147,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -167,7 +167,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -184,7 +184,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -193,7 +193,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -357,11 +357,26 @@ "source": [ "estimated_contact_matrix" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "diff = estimated_C \n", + "\n", + "plt.figure(figsize=(10, 8))\n", + "plt.imshow(diff, cmap = 'coolwarm', interpolation='none')\n", + "plt.colorbar(label = 'Diff')" + ] } ], "metadata": { "kernelspec": { - "display_name": ".venv", + "display_name": "Python 3", "language": "python", "name": "python3" }, @@ -375,7 +390,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.12.7" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/dist/dp_epidemiology-0.0.9.tar.gz b/dist/dp_epidemiology-0.0.9.tar.gz deleted file mode 100644 index 03eb266..0000000 Binary files a/dist/dp_epidemiology-0.0.9.tar.gz and /dev/null differ diff --git a/dist/dp_epidemiology-0.0.9-py3-none-any.whl b/dist/dp_epidemiology-0.1.0-py3-none-any.whl similarity index 51% rename from dist/dp_epidemiology-0.0.9-py3-none-any.whl rename to dist/dp_epidemiology-0.1.0-py3-none-any.whl index f58ac60..3e49bca 100644 Binary files a/dist/dp_epidemiology-0.0.9-py3-none-any.whl and b/dist/dp_epidemiology-0.1.0-py3-none-any.whl differ diff --git a/dist/dp_epidemiology-0.1.0.tar.gz b/dist/dp_epidemiology-0.1.0.tar.gz new file mode 100644 index 0000000..89e35e0 Binary files /dev/null and b/dist/dp_epidemiology-0.1.0.tar.gz differ diff --git a/pyproject.toml b/pyproject.toml index e100188..abbd468 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "DP_epidemiology" -version = "0.0.9" +version = "0.1.0" dependencies = [ "pandas>=2.1.4", diff --git a/src/DP_epidemiology/utilities.py b/src/DP_epidemiology/utilities.py index e205560..6525db3 100644 --- a/src/DP_epidemiology/utilities.py +++ b/src/DP_epidemiology/utilities.py @@ -397,5 +397,6 @@ def time_preprocess(df): # Filter the dataframe based on the category df_final = df_weekly[["date", category]] + df_final[category] = (df_final[category] - df_final[category].min()) / (df_final[category].max() - df_final[category].min()) return df_final