Update tests

.github/workflows/python-app.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-latest]   #windows-latest
+        os: [ubuntu-latest, windows-latest]   #macos-latest fails because no matching distribution found for nvidia-cublas-cu12==12.1.3.1
         python-version: ["3.10"]  
 
     steps:  
@@ -24,19 +24,20 @@ jobs:
           python-version: ${{ matrix.python-version }}  
       - name: Install dependencies  
         run: |  
-          python -m pip install --upgrade pip  
-          pip install .  
-          pip install .[dev]   
+          python -m pip install --upgrade pip setuptools wheel
+          if [ -f dev-requirements.txt ]; then pip install -r dev-requirements.txt; fi  
         continue-on-error: false
-      - name: Run Ruff
-        run: ruff check --fix --config=pyproject.toml --output-format=github .
+      - name: Run Ruff 
+        run: ruff check --output-format=github .
       - name: Test with pytest  
         run: |  
           coverage run -m pytest  -v -s  
       - name: Generate Coverage Report  
         run: |  
           coverage report -m
-      - name: test if app starts
-        run: | #do I need to exit this step?
-          cd /synthetic_data_talk
-          streamlit run 🔓_Synthetic_Data.py
+      - name: test streamlit app
+        uses: streamlit/streamlit-app-action@v0.0.3
+        with:
+          app-path: synthetic_data_talk/🔓_Synthetic_Data.py
+          ruff: true
+

demo_notebooks/demo_ctgan_best_setting.ipynb

@@ -6,15 +6,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import warnings\n",
     "import json\n",
     "import os\n",
+    "import warnings\n",
+    "\n",
+    "import pandas as pd\n",
     "\n",
     "os.chdir(\"/home/antonia/code/Unlocking-Information-Creating-Synthetic-Data-for-Open-Access\") # insert your your path to the project here\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "\n",
-    "folder_name = 'best_setting'"
+    "folder_name = \"best_setting\""
    ]
   },
   {
@@ -31,7 +32,7 @@
     }
    ],
    "source": [
-    "rpad_df = pd.read_excel(r'data/RPAD_data_small.xlsx', engine='openpyxl')\n",
+    "rpad_df = pd.read_excel(r\"data/RPAD_data_small.xlsx\", engine=\"openpyxl\")\n",
     "print(rpad_df.shape)"
    ]
   },
@@ -121,7 +122,7 @@
     "def calculate_bmi(weight, height):\n",
     "   return weight/(height/100)**2\n",
     "\n",
-    "rpad_df.drop(rpad_df[round(rpad_df['BMI'],0) != round(calculate_bmi(rpad_df['Weight'], rpad_df['Height']),0)].index, inplace=True)\n",
+    "rpad_df.drop(rpad_df[round(rpad_df[\"BMI\"],0) != round(calculate_bmi(rpad_df[\"Weight\"], rpad_df[\"Height\"]),0)].index, inplace=True)\n",
     "print(rpad_df.shape)"
    ]
   },
@@ -133,15 +134,15 @@
    "source": [
     "# load the constraint from the file\n",
     "model.load_custom_constraint_classes(\n",
-    "    filepath='/home/antonia/code/Unlocking-Information/utils/example_custom_constraint.py',\n",
-    "    class_names=['BMI_Formulae']\n",
+    "    filepath=\"/home/antonia/code/Unlocking-Information/utils/example_custom_constraint.py\",\n",
+    "    class_names=[\"BMI_Formulae\"],\n",
     ")\n",
     "\n",
     "constraint = {\n",
-    "    'constraint_class': 'BMI_Formulae',\n",
-    "    'constraint_parameters': {\n",
-    "        'column_names': ['BMI', 'Weight', 'Height']\n",
-    "    }\n",
+    "    \"constraint_class\": \"BMI_Formulae\",\n",
+    "    \"constraint_parameters\": {\n",
+    "        \"column_names\": [\"BMI\", \"Weight\", \"Height\"],\n",
+    "    },\n",
     "}"
    ]
   },
@@ -153,19 +154,19 @@
    "source": [
     "def get_positive_constraint(column_name, strict):\n",
     "    return {\n",
-    "       'constraint_class': 'Positive',\n",
-    "       'constraint_parameters': {\n",
-    "           'column_name': column_name,\n",
-    "           'strict_boundaries': strict\n",
+    "       \"constraint_class\": \"Positive\",\n",
+    "       \"constraint_parameters\": {\n",
+    "           \"column_name\": column_name,\n",
+    "           \"strict_boundaries\": strict,\n",
+    "       },\n",
     "       }\n",
-    "       }\n",
-    "positive_bmi = get_positive_constraint('BMI', True)\n",
-    "positive_weight = get_positive_constraint('Weight', True)\n",
-    "positive_height = get_positive_constraint('Height', True)\n",
-    "positive_los = get_positive_constraint('Length_of_Stay', True)\n",
-    "positive_age = get_positive_constraint('Age', False)\n",
-    "positive_a_score = get_positive_constraint('Alvarado_Score', False)\n",
-    "positive_pa_score = get_positive_constraint('Paedriatic_Appendicitis_Score', False)"
+    "positive_bmi = get_positive_constraint(\"BMI\", True)\n",
+    "positive_weight = get_positive_constraint(\"Weight\", True)\n",
+    "positive_height = get_positive_constraint(\"Height\", True)\n",
+    "positive_los = get_positive_constraint(\"Length_of_Stay\", True)\n",
+    "positive_age = get_positive_constraint(\"Age\", False)\n",
+    "positive_a_score = get_positive_constraint(\"Alvarado_Score\", False)\n",
+    "positive_pa_score = get_positive_constraint(\"Paedriatic_Appendicitis_Score\", False)"
    ]
   },
   {
@@ -299,7 +300,7 @@
     "quality_report = evaluate_quality(\n",
     "    rpad_df,\n",
     "    synth_data,\n",
-    "    metadata\n",
+    "    metadata,\n",
     ")\n",
     "\n",
     "quality_report.save(filepath=f\"pages/evaluation/{folder_name}/results/quality_report.pkl\")"
@@ -378,10 +379,10 @@
          "y": [
           0.934156378600823,
           0.8244170096021948,
-          0.9506172839506173,
+          0.9506172839506172,
           0.9122085048010974,
           0.874828060522696,
-          0.9324393603016887,
+          0.9324393603016888,
           0.9042516216204474
          ],
          "yaxis": "y"
@@ -425,7 +426,7 @@
          ],
          "xaxis": "x",
          "y": [
-          0.9876543209876543,
+          0.9876543209876544,
           0.887517146776406,
           0.8710562414266118
          ],
@@ -1296,7 +1297,7 @@
     }
    ],
    "source": [
-    "fig = quality_report.get_visualization('Column Shapes')\n",
+    "fig = quality_report.get_visualization(\"Column Shapes\")\n",
     "fig.show()\n",
     "fig.write_image(file = f\"pages/evaluation/{folder_name}/images/col_shapes.png\")"
    ]
@@ -3680,10 +3681,10 @@
     "fig = get_column_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_name='Sex',\n",
-    "    metadata=metadata\n",
+    "    column_name=\"Sex\",\n",
+    "    metadata=metadata,\n",
     ")\n",
-    "    \n",
+    "\n",
     "fig.show()\n",
     "fig.write_image(file = f\"pages/evaluation/{folder_name}/images/col_plot_sex.png\")\n"
    ]
@@ -11384,18 +11385,18 @@
     "fig_categorical = get_column_pair_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_names=['Severity', 'Management'],\n",
+    "    column_names=[\"Severity\", \"Management\"],\n",
     "    metadata=metadata)\n",
-    "    \n",
+    "\n",
     "fig_categorical.show()\n",
     "fig_categorical.write_image(file = f\"pages/evaluation/{folder_name}/images/Severity_Management_pair_plot.png\")\n",
     "\n",
     "fig_numerical = get_column_pair_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_names=['Weight', 'Height'],\n",
+    "    column_names=[\"Weight\", \"Height\"],\n",
     "    metadata=metadata)\n",
-    "    \n",
+    "\n",
     "fig_numerical.show()\n",
     "fig_numerical.write_image(file = f\"pages/evaluation/{folder_name}/images/Weight_Height_pair_plot.png\")"
    ]

demo_notebooks/demo_ctgan_default.ipynb

@@ -6,14 +6,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import warnings\n",
     "import os\n",
+    "import warnings\n",
+    "\n",
+    "import pandas as pd\n",
     "\n",
     "os.chdir(\"/path/to/your/project/\") # insert your your path to the project here\n",
     "warnings.filterwarnings(\"ignore\")\n",
     "\n",
-    "folder_name = 'default'"
+    "folder_name = \"default\""
    ]
   },
   {
@@ -30,7 +31,7 @@
     }
    ],
    "source": [
-    "rpad_df = pd.read_excel(r'data/RPAD_data_small.xlsx', engine='openpyxl')\n",
+    "rpad_df = pd.read_excel(r\"data/RPAD_data_small.xlsx\", engine=\"openpyxl\")\n",
     "print(rpad_df.shape)\n",
     "# print(rpad_df.head(5))"
    ]
@@ -192,7 +193,7 @@
     "quality_report = evaluate_quality(\n",
     "    rpad_df,\n",
     "    synth_data,\n",
-    "    metadata\n",
+    "    metadata,\n",
     ")\n",
     "\n",
     "quality_report.save(filepath=f\"pages/evaluation/{folder_name}/results/quality_report.pkl\")"
@@ -1195,7 +1196,7 @@
     }
    ],
    "source": [
-    "fig = quality_report.get_visualization('Column Shapes')\n",
+    "fig = quality_report.get_visualization(\"Column Shapes\")\n",
     "fig.show()\n",
     "fig.write_image(file = f\"pages/evaluation/{folder_name}/images/col_shapes.png\")"
    ]
@@ -3695,10 +3696,10 @@
     "fig = get_column_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_name='Sex',\n",
-    "    metadata=metadata\n",
+    "    column_name=\"Sex\",\n",
+    "    metadata=metadata,\n",
     ")\n",
-    "    \n",
+    "\n",
     "fig.show()\n",
     "fig.write_image(file = f\"pages/evaluation/{folder_name}/images/col_plot_sex.png\")\n"
    ]
@@ -11823,18 +11824,18 @@
     "fig_categorical = get_column_pair_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_names=['Severity', 'Management'],\n",
+    "    column_names=[\"Severity\", \"Management\"],\n",
     "    metadata=metadata)\n",
-    "    \n",
+    "\n",
     "fig_categorical.show()\n",
     "fig_categorical.write_image(file = f\"pages/evaluation/{folder_name}/images/Severity_Management_pair_plot.png\")\n",
     "\n",
     "fig_numerical = get_column_pair_plot(\n",
     "    real_data=rpad_df,\n",
     "    synthetic_data=synth_data,\n",
-    "    column_names=['Weight', 'Height'],\n",
+    "    column_names=[\"Weight\", \"Height\"],\n",
     "    metadata=metadata)\n",
-    "    \n",
+    "\n",
     "fig_numerical.show()\n",
     "fig_numerical.write_image(file = f\"pages/evaluation/{folder_name}/images/Weight_Height_pair_plot.png\")"
    ]