Merge branch 'main' of https://github.com/KnowledgeEdgeAI/PETs_for_Pu…

…blic_Health_Challenge
KnowledgeEdgeAI · Nov 14, 2024 · 8a5a554 · 8a5a554
2 parents 754bd7c + 026cac0
commit 8a5a554
Show file tree

Hide file tree

Showing 7 changed files with 67 additions and 51 deletions.
diff --git 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
@@ -24,7 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -49,10 +49,10 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>ID</th>\n",
+       "      <th>date</th>\n",
        "      <th>merch_category</th>\n",
        "      <th>merch_postal_code</th>\n",
        "      <th>transaction_type</th>\n",
-       "      <th>date</th>\n",
        "      <th>spendamt</th>\n",
        "      <th>nb_transactions</th>\n",
        "    </tr>\n",
@@ -61,80 +61,80 @@
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>1</td>\n",
-       "      <td>Hospitals</td>\n",
-       "      <td>111921</td>\n",
-       "      <td>ONLINE</td>\n",
        "      <td>2019-01-01</td>\n",
-       "      <td>80797.323317</td>\n",
-       "      <td>398</td>\n",
+       "      <td>Grocery Stores/Supermarkets</td>\n",
+       "      <td>8700000</td>\n",
+       "      <td>ONLINE</td>\n",
+       "      <td>11238.128450</td>\n",
+       "      <td>160</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>2</td>\n",
-       "      <td>Bars/Discotheques</td>\n",
-       "      <td>050025</td>\n",
-       "      <td>OFFLINE</td>\n",
+       "      <td>1</td>\n",
        "      <td>2019-01-01</td>\n",
-       "      <td>5331.031100</td>\n",
-       "      <td>283</td>\n",
+       "      <td>Grocery Stores/Supermarkets</td>\n",
+       "      <td>500034</td>\n",
+       "      <td>ONLINE</td>\n",
+       "      <td>12848.165221</td>\n",
+       "      <td>183</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>2</td>\n",
-       "      <td>Bars/Discotheques</td>\n",
-       "      <td>050032</td>\n",
-       "      <td>OFFLINE</td>\n",
        "      <td>2019-01-01</td>\n",
-       "      <td>5180.722635</td>\n",
-       "      <td>268</td>\n",
+       "      <td>Grocery Stores/Supermarkets</td>\n",
+       "      <td>110621</td>\n",
+       "      <td>ONLINE</td>\n",
+       "      <td>12116.165569</td>\n",
+       "      <td>173</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>3</td>\n",
-       "      <td>Drug Stores/Pharmacies</td>\n",
-       "      <td>050012</td>\n",
-       "      <td>OFFLINE</td>\n",
        "      <td>2019-01-01</td>\n",
-       "      <td>5032.333763</td>\n",
-       "      <td>177</td>\n",
+       "      <td>Hotels/Motels</td>\n",
+       "      <td>8900000</td>\n",
+       "      <td>OFFLINE</td>\n",
+       "      <td>7745.998879</td>\n",
+       "      <td>38</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>3</td>\n",
-       "      <td>Drug Stores/Pharmacies</td>\n",
-       "      <td>050031</td>\n",
-       "      <td>OFFLINE</td>\n",
+       "      <td>4</td>\n",
        "      <td>2019-01-01</td>\n",
-       "      <td>4899.182326</td>\n",
-       "      <td>150</td>\n",
+       "      <td>Restaurants</td>\n",
+       "      <td>111941</td>\n",
+       "      <td>OFFLINE</td>\n",
+       "      <td>6927.424754</td>\n",
+       "      <td>173</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "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
diff --git a/dist/dp_epidemiology-0.0.9-py3-none-any.whl → dist/dp_epidemiology-0.1.0-py3-none-any.whl b/dist/dp_epidemiology-0.0.9-py3-none-any.whl → dist/dp_epidemiology-0.1.0-py3-none-any.whl
diff --git a/dist/dp_epidemiology-0.1.0.tar.gz b/dist/dp_epidemiology-0.1.0.tar.gz
diff --git 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
@@ -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