docs: update and fix documentatio and package examples

Author: Fabiana Clemente

docs/getting-started/installation.md

@@ -12,9 +12,13 @@ If you are in a notebook (locally, LambdaLabs, Google Colab or Kaggle), you can
 ```python linenums="1"
     import sys
     !{sys.executable} -m pip install -U ydata-profiling[notebook]
-    !jupyter nbextension enable --py widgetsnbextension
+    !pip install jupyter-contrib-nbextensions
 ```
+Afterwards you can run the following command
 
+```python linenums="1"
+    !jupyter nbextension enable --py widgetsnbextension
+```
 You may have to restart the kernel or runtime for the package to work.
 
 ## Using conda

examples/integrations/ydata_fabric_pipelines/data_profiling.ipynb

@@ -11,9 +11,6 @@
      "start_time": "2022-10-24T06:29:02.519523",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%% md\n"
-    },
     "tags": []
    },
    "source": [
@@ -31,9 +28,6 @@
      "start_time": "2022-10-24T06:29:02.636283",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%% md\n"
-    },
     "tags": []
    },
    "source": [
@@ -57,9 +51,6 @@
      "start_time": "2022-10-24T06:29:02.737117",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%% md\n"
-    },
     "tags": []
    },
    "source": [
@@ -77,9 +68,6 @@
      "start_time": "2022-10-24T06:29:06.291913",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%% md\n"
-    },
     "tags": []
    },
    "source": [
@@ -98,9 +86,6 @@
      "start_time": "2022-10-24T06:29:06.401327",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],
@@ -127,14 +112,11 @@
      "start_time": "2022-10-24T06:29:08.641388",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],
    "source": [
-    "dataset = DataSources.get(uid=\"973d95c7-e6bd-4535-a0ea-d3dd1e893b13\").read()"
+    "dataset = DataSources.get(uid=\"insert-uid\").read()"
    ]
   },
   {
@@ -149,9 +131,6 @@
      "start_time": "2022-10-24T06:29:14.867782",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],
@@ -171,9 +150,6 @@
      "start_time": "2022-10-24T06:29:15.001031",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%% md\n"
-    },
     "tags": []
    },
    "source": [
@@ -192,9 +168,6 @@
      "start_time": "2022-10-24T06:29:15.107441",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],
@@ -215,9 +188,6 @@
      "start_time": "2022-10-24T06:29:15.322696",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],
@@ -244,9 +214,6 @@
      "start_time": "2022-10-24T06:29:51.135648",
      "status": "completed"
     },
-    "pycharm": {
-     "name": "#%%\n"
-    },
     "tags": []
    },
    "outputs": [],

examples/meteorites/meteorites.ipynb

@@ -40,7 +40,8 @@
    "source": [
     "import sys\n",
     "\n",
-    "!{sys.executable} -m pip install -U pandas-profiling[notebook]\n",
+    "!{sys.executable} -m pip install -U ydata-profiling[notebook]\n",
+    "!pip install jupyter-contrib-nbextensions\n",
     "!jupyter nbextension enable --py widgetsnbextension"
    ]
   },

examples/meteorites/meteorites_cloud.ipynb

@@ -21,7 +21,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -U pandas-profiling"
+    "!pip install -U ydata-profiling"
    ]
   },
   {

examples/titanic/titanic.ipynb

@@ -32,7 +32,8 @@
    "source": [
     "import sys\n",
     "\n",
-    "!\"{sys.executable}\" -m pip install -U pandas-profiling[notebook]\n",
+    "!\"{sys.executable}\" -m pip install -U ydata-profiling[notebook]\n",
+    "!pip install jupyter-contrib-nbextensions\n",
     "!jupyter nbextension enable --py widgetsnbextension"
    ]
   },

examples/titanic/titanic_cloud.ipynb

@@ -13,7 +13,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -U pandas-profiling"
+    "!pip install -U ydata-profiling"
    ]
   },
   {

examples/usaairquality/usaairquality.ipynb

@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "b514dd38-2ebd-4c96-aed5-4e3695e20fa2",
    "metadata": {},
    "outputs": [],
@@ -47,6 +47,7 @@
     "import sys\n",
     "\n",
     "!{sys.executable} -m pip install -U pandas-profiling[notebook]\n",
+    "!pip install jupyter-contrib-nbextensions\n",
     "!jupyter nbextension enable --py widgetsnbextension"
    ]
   },
@@ -68,7 +69,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "b33a26ed-4e1e-4689-93ce-fa0f98f48e89",
    "metadata": {},
    "outputs": [],
@@ -89,7 +90,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "7dab0b47-537d-4402-af71-1bdfd0cf6cdd",
    "metadata": {},
    "outputs": [],
@@ -139,10 +140,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "15e613a6",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/fabianaclemente/miniconda3/envs/yprof/lib/python3.11/site-packages/ydata_profiling/visualisation/plot.py:835: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
+      "  df = df.groupby([entity_column, \"__bins\"])[sortbykey].count()\n",
+      "/Users/fabianaclemente/miniconda3/envs/yprof/lib/python3.11/site-packages/ydata_profiling/visualisation/plot.py:836: FutureWarning: The default value of observed=False is deprecated and will change to observed=True in a future version of pandas. Specify observed=False to silence this warning and retain the current behavior\n",
+      "  df = df.reset_index().pivot_table(entity_column, \"__bins\", sortbykey).T\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='Time'>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "from ydata_profiling.visualisation.plot import timeseries_heatmap\n",
     "\n",
@@ -151,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "b29a7e78-d52d-458d-ac9a-e509ffd373d1",
    "metadata": {},
    "outputs": [],
@@ -168,6 +200,88 @@
     "\n",
     "    profile.to_file(f\"Ts_Profile_{group[0]}.html\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7327cb70-3db8-441e-837e-4ac2a5a57eaa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ac531d9e9574493083522ec56b68c3cc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6ccba6e512c84b01be36afb26e250000",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Render widgets:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "427e682fb36b4017a8f1db4f714bb5e3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Tab(children=(Tab(children=(GridBox(children=(VBox(children=(GridspecLayout(children=(HTML(valu…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "profile = ProfileReport(\n",
+    "    group[1],\n",
+    "    tsmode=True,\n",
+    "    sortby=\"Date Local\",\n",
+    "    # title=f\"Air Quality profiling - Site Num: {group[0]}\"\n",
+    ")\n",
+    "\n",
+    "profile.to_file()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c53d119-d014-4104-a5b2-76fd7a45181e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -186,7 +300,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.11.9"
   },
   "varInspector": {
    "cols": {

examples/zero_division.py

@@ -0,0 +1,20 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+
+if __name__ == '__main__':
+    import numpy as np
+
+    df = pd.read_csv("c6cb4c3d-e735-4b55-bd5c-b7c78ab152aa.csv", sep=',', encoding = "latin")
+    #df['empty_col'] = [None]*len(df)
+
+    df.sample(10000)
+
+    df.to_csv('Validation.csv')
+
+
+    #df.to_csv('teste.csv')
+
+    report = ProfileReport(df, title='Testing the null values')
+    report.to_file('report.html')
+