add tabulate output. ref #75

tompollard · Nov 18, 2019 · 061b9a5 · 061b9a5
1 parent 900bbfb
commit 061b9a5
Show file tree

Hide file tree

Showing 4 changed files with 101 additions and 26 deletions.
diff --git a/README.md b/README.md
@@ -76,17 +76,17 @@ labels={'death': 'mortality'}
 mytable = TableOne(data, columns, categorical, groupby, nonnormal, rename=labels, pval=False)
 ```
 
-7. Type the name of the instance in an interpreter:
+7. Display the table using the `tabulate` method. The `tablefmt` argument allows the table to be displayed in multiple formats, including "github", "grid", "fancy_grid", "rst", "html", and "latex".
 
 ```python
-mytable
+print(overall_table.tabulate(tablefmt = "fancy_grid"))
 ```
 
 8. ...which prints the following table to screen:
 
 Grouped by mortality:
 
-| variable  | level  | missing  |        0       |        1       | 
+|           |        | Missing  |        0       |        1       | 
 | --------- | ------ | -------- | -------------- | -------------- | 
 | n         |        |          | 864            | 136            |
 | Age       |        |  0       | 66 [52,78]     | 75 [62,83]     |
@@ -105,5 +105,3 @@ Grouped by mortality:
 ```python
 mytable.to_excel('mytable.xlsx')
 ```
-
-
diff --git a/README.rst b/README.rst
@@ -87,9 +87,9 @@ Example
 
     mytable = TableOne(data, columns, categorical, groupby, nonnormal)
 
-#. Type the name of the instance in an interpreter::
+#. Display the table using the ``tabulate`` method. The ``tablefmt`` argument allows the table to be displayed in multiple formats, including "github", "grid", "fancy_grid", "rst", "html", and "latex".::
 
-    mytable
+    print(mytable.tabulate(tablefmt="github"))
 
 #. ...which prints the following table to screen::
 

diff --git a/tableone.ipynb b/tableone.ipynb
@@ -400,6 +400,47 @@
     "- if `label_suffix=True`, \"mean (SD); n (%);\" etc are appended to the row label."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Displaying the table in custom formats\n",
+    "\n",
+    "The tableone object includes a `tabulate` method, that makes use of the [tabulate](https://pypi.org/project/tabulate/) package to display the table in custom output formats. Supported table formats include: \"github\", \"grid\", \"fancy_grid\", \"rst\", \"html\", \"latex\", and \"latex_raw\". See the tabulate package for more formats."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "|                   |      | Missing   | Overall      |\n",
+      "|-------------------|------|-----------|--------------|\n",
+      "| n                 |      |           | 1000         |\n",
+      "| Age, mean (SD)    |      | 0         | 65.0 (17.2)  |\n",
+      "| SysABP, mean (SD) |      | 291       | 114.3 (40.2) |\n",
+      "| Height, mean (SD) |      | 475       | 170.1 (22.1) |\n",
+      "| Weight, mean (SD) |      | 302       | 82.9 (23.8)  |\n",
+      "| ICU, n (%)        | CCU  | 0         | 162 (16.2)   |\n",
+      "|                   | CSRU |           | 202 (20.2)   |\n",
+      "|                   | MICU |           | 380 (38.0)   |\n",
+      "|                   | SICU |           | 256 (25.6)   |\n",
+      "| MechVent, n (%)   | 0    | 0         | 540 (54.0)   |\n",
+      "|                   | 1    |           | 460 (46.0)   |\n",
+      "| LOS, mean (SD)    |      | 0         | 14.2 (14.2)  |\n",
+      "| death, n (%)      | 0    | 0         | 864 (86.4)   |\n",
+      "|                   | 1    |           | 136 (13.6)   |\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(overall_table.tabulate(tablefmt = \"github\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -411,7 +452,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -420,7 +461,7 @@
        "(-30, 250)"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -454,7 +495,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -493,7 +534,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -607,7 +648,7 @@
        "[3] Warning, test for normality reports non-normal distributions for: Age, SysABP, Height, Weight."
       ]
      },
-     "execution_count": 9,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -656,7 +697,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -669,7 +710,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -679,7 +720,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -811,7 +852,7 @@
        "[3] Warning, test for normality reports non-normal distributions for: Age, Height, SysABP, Weight."
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -841,7 +882,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -851,7 +892,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -884,8 +925,8 @@
        "      <th>Missing</th>\n",
        "      <th>0</th>\n",
        "      <th>1</th>\n",
-       "      <th>pval</th>\n",
-       "      <th>ptest</th>\n",
+       "      <th>p-value</th>\n",
+       "      <th>Test</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -990,7 +1031,7 @@
       ],
       "text/plain": [
        "                         Grouped by death                                                               \n",
-       "                                  Missing                 0                 1    pval              ptest\n",
+       "                                  Missing                 0                 1 p-value               Test\n",
        "n                                                       864               136                           \n",
        "Age, median [Q1,Q3]                     0  66.0 [52.8,78.0]  75.0 [62.0,83.0]  <0.001     Kruskal-Wallis\n",
        "SysABP, mean (SD)                     291      115.4 (38.3)      107.6 (49.4)   0.134  Two Sample T-test\n",
@@ -1007,7 +1048,7 @@
        "[3] Warning, test for normality reports non-normal distributions for: Age, Height, SysABP, Weight."
       ]
      },
-     "execution_count": 14,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1042,7 +1083,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1053,7 +1094,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1064,7 +1105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [

diff --git a/tableone.py b/tableone.py
@@ -12,6 +12,7 @@
 import pandas as pd
 from scipy import stats
 from statsmodels.stats import multitest
+from tabulate import tabulate
 
 import modality
 
@@ -226,6 +227,41 @@ def __repr__(self):
     def _repr_html_(self):
         return self.tableone._repr_html_() + self._generate_remark_str('<br />')
 
+    def tabulate(self, headers=None, tablefmt='grid', **kwargs):
+        """
+        Pretty-print tableone data. Wrapper for the Python 'tabulate' library.
+
+        Args:
+            headers (list): Defines a list of column headers to be used.
+            tablefmt (str): Defines how the table is formatted. Table formats
+                include: 'plain','simple','github','grid','fancy_grid','pipe',
+                'orgtbl','jira','presto','psql','rst','mediawiki','moinmoin',
+                'youtrack','html','latex','latex_raw','latex_booktabs',
+                and 'textile'.
+
+        Examples:
+            To output tableone in github syntax, call tabulate with the
+                'tablefmt=github' argument.
+
+            >>> print(tableone.tabulate(tablefmt='fancy_grid'))
+        """
+        # reformat table for tabulate
+        df = self.tableone
+
+        if not headers:
+            try:
+                headers = df.columns.levels[1]
+            except AttributeError:
+                headers = df.columns
+
+        df = df.reset_index()
+        df = df.set_index('level_0')
+        isdupe = df.index.duplicated()
+        df.index = df.index.where(~isdupe, '')
+        df = df.rename_axis(None).rename(columns={'level_1': ''})
+
+        return tabulate(df, headers=headers, tablefmt=tablefmt, **kwargs)
+
     def _generate_remark_str(self, end_of_line='\n'):
         """
         Generate a series of remarks that the user should consider
@@ -886,7 +922,7 @@ def _create_tableone(self, data):
             pass
 
         # remove the 'variable, value' column names in the index
-        table = table.rename_axis([None,None])
+        table = table.rename_axis([None, None])
 
         return table