Merge pull request #15 from ACCLAB/v0.1.3

v0.1.3

LICENSE

@@ -1,6 +1,6 @@
 The Clear BSD License
 
-Copyright (c) 2016-2017 Joses W. Ho
+Copyright (c) 2016-2018 Joses W. Ho
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

README.md

@@ -1,6 +1,6 @@
 # DABEST (Python)
 [![Travis CI](https://travis-ci.org/ACCLAB/DABEST-python.svg?branch=master)](https://travis-ci.org/ACCLAB/DABEST-python)
-[![PyPI](https://img.shields.io/pypi/v/dabest.svg)](https://pypi.python.org/pypi/dabest/0.1.1)
+[![PyPI](https://img.shields.io/pypi/v/dabest.svg)](https://pypi.python.org/pypi/dabest/0.1.3)
 
 ## About
 
@@ -17,7 +17,7 @@ In addition, the following packages are also required:
 - [scipy](https://www.scipy.org/) (1.0.x)
 - [matplotlib](https://www.matplotlib.org/) (2.0.x)
 - [seaborn](https://seaborn.pydata.org/) (0.8.x)
-- [pandas](https://pandas.pydata.org/) (0.22.x).
+- [pandas](https://pandas.pydata.org/) (0.23.x).
 
 To obtain these package dependencies easily, it is highly recommended to download the [Anaconda distribution](https://www.continuum.io/downloads) of Python.
 
@@ -42,10 +42,19 @@ Then, navigate to the cloned repo in the command line and run
 pip install .
 ```
 
+
 ## Usage
 
 Please refer to the [documentation](https://acclab.github.io/DABEST-python-docs/index.html).
 
+
 ## Matlab version
 
 There is also a [Matlab version](https://github.com/ACCLAB/DABEST-Matlab) of DABEST.
+
+
+## R version
+
+There isn't an implementation of DABEST in R, and there are no current plans to create one.
+
+However, it is possible to use the R package `reticulate` to run Python code. Please take a look at this [tutorial](https://acclab.github.io/DABEST-python-docs/dabest-r.html) on how to use `reticulate` to analyse data in R.

dabest/__init__.py

@@ -2,4 +2,4 @@
 from .api import plot
 from .bootstrap_tools import bootstrap
 
-__version__="0.1.2"
+__version__="0.1.3"

dabest/api.py

@@ -1,3 +1,8 @@
+#!/usr/bin/python
+# -*-coding: utf-8 -*-
+# Author: Joses Ho
+# Email : [email protected]
+
 
 
 def plot(data, idx,
@@ -732,5 +737,9 @@ def plot(data, idx,
         value=np.nan).dropna(axis=1)
     # Reset seaborn aesthetic parameters.
     sns.set()
+
+    if swarm_label is not None:
+        fig.axes[0].set_ylabel(swarm_label)
+
     # Return the figure and the results DataFrame.
     return fig, bootlist_df

dabest/bootstrap_tools.py

@@ -1,3 +1,9 @@
+#!/usr/bin/python
+# -*-coding: utf-8 -*-
+# Author: Joses Ho
+# Email : [email protected]
+
+
 from __future__ import division
 
 
@@ -160,7 +166,7 @@ def __init__(self, x1, x2=None,
 
             else:
                 diff = True
-                tx = x2-x1
+                tx = x2 - x1
                 ttest_single = 'NIL'
                 ttest_2_ind = 'NIL'
                 ttest_2_paired = ttest_rel(x1,x2)[1]
@@ -183,6 +189,7 @@ def __init__(self, x1, x2=None,
 
         elif x2 is not None and paired is False:
             diff = True
+            x2 = pd.Series(x2).dropna()
             # Generate statarrays for both arrays.
             ref_statarray = sns.algorithms.bootstrap(x1, **sns_bootstrap_kwargs)
             exp_statarray = sns.algorithms.bootstrap(x2, **sns_bootstrap_kwargs)
@@ -290,6 +297,8 @@ def bca(data, alphas, statarray, statfunction, ostat, reps):
     Subroutine called to calculate the BCa statistics.
     Borrowed heavily from scikits.bootstrap code.
     '''
+    import warnings
+
     import numpy as np
     import pandas as pd
     import seaborn as sns

dabest/misc_tools.py

@@ -1,3 +1,8 @@
+#!/usr/bin/python
+# -*-coding: utf-8 -*-
+# Author: Joses Ho
+# Email : [email protected]
+
 # CONVENIENCE FUNCTIONS THAT DON'T DIRECTLY DEAL WITH PLOTTING OR
 # BOOTSTRAP COMPUTATIONS ARE PLACED HERE.
 

dabest/plot_tools.py

@@ -1,10 +1,9 @@
-"""
-A set of convenience functions used for producing plots in `dabest`.
+#!/usr/bin/python
+# -*-coding: utf-8 -*-
+# Author: Joses Ho
+# Email : [email protected]
+# A set of convenience functions used for producing plots in `dabest`.
 
-Author: Joses W. Ho
-Email: [email protected]
-License: MIT
-"""
 
 
 import matplotlib.pyplot as plt
@@ -14,6 +13,7 @@
 from .misc_tools import merge_two_dicts
 
 
+
 def halfviolin(v, half = 'right', color = 'k'):
     for b in v['bodies']:
             mVertical = np.mean(b.get_paths()[0].vertices[:, 0])
@@ -33,6 +33,8 @@ def halfviolin(v, half = 'right', color = 'k'):
                                                     mHorizontal, np.inf)
             b.set_color(color)
 
+
+
 def align_yaxis(ax1, v1, ax2, v2):
     """adjust ax2 ylimit so that v2 in ax2 is aligned to v1 in ax1"""
     # Taken from
@@ -50,90 +52,7 @@ def rotate_ticks(axes, angle=45, alignment='right'):
         tick.set_rotation(angle)
         tick.set_horizontalalignment(alignment)
 
-def tufte_summary_line(df, x, y, type='mean_sd',
-                       offset=0.3, ax=None, **kwargs):
-    '''Convenience function to plot sumamry statistics (mean and standard
-    deviation, or median and 25th & 75th percentiles) for ach group in the `x`
-    column of `df`. This style is inspired by Edward Tufte.
-
-    Keywords
-    --------
-    data: pandas DataFrame.
-        This DataFrame should be in 'long' format.
-
-    x, y: string.
-        x and y columns to be plotted.
-
-    type: {'mean_sd', 'median_quartiles'}, default 'mean_sd'
-        Plots the summary statistics for each group. If 'mean_sd', then the
-        mean and standard deviation of each group is plotted as a notched
-        line beside each group. If 'median_quantile', then the
-        median and 25th and 75th percentiles of each group is plotted
-        instead.
-
-    offset: float, default 0.4
-        The x-offset of the summary line.
-
-    offset: matplotlib Axes, default None
-        If specified, the axes to plot on.
-
-    kwargs: dict, default None
-        Dictionary with kwargs passed to `matplotlib.patches.FancyArrow`.
-        See docs at
-        https://matplotlib.org/api/_as_gen/
-        matplotlib.patches.FancyArrow.html#matplotlib.patches.FancyArrow
-
-    '''
-    import matplotlib.patches as mpatches
-
-    if ax is None:
-        ax = plt.gca()
-
-    means = df.groupby(x)[y].mean()
-    sd = df.groupby(x)[y].std()
-    lower_sd = means - sd
-    upper_sd = means + sd
 
-    medians = df.groupby(x)[y].median()
-    quantiles = df.groupby(x)[y].quantile([0.25, 0.75]).unstack()
-    lower_quartiles = quantiles[0.25]
-    upper_quartiles = quantiles[0.75]
-
-    if type == 'mean_sd':
-        central_measures = means
-        low = lower_sd
-        high = upper_sd
-    elif type == 'median_quartiles':
-        central_measures = medians
-        low = lower_quartiles
-        high = upper_quartiles
-
-    total_width = 0.05 # the horizontal span of the line, aka `linewidth`.
-
-    for k, m in enumerate(central_measures):
-
-        kwargs['dx'] = 0
-        kwargs['width'] = total_width
-        kwargs['head_width'] = total_width
-        kwargs['length_includes_head'] = True
-
-        if type == 'mean_sd':
-            dy_low = dy_high = sd[k]
-        elif type == 'median_quartiles':
-            dy_low = m - low[k]
-            dy_high = high[k] - m
-
-        arrow = mpatches.FancyArrow(x=offset+k, y=low[k],
-                                    dy=dy_low,
-                                    head_length=0.3*dy_low,
-                                    **kwargs)
-        ax.add_patch(arrow)
-
-        arrow = mpatches.FancyArrow(x=offset+k, y=high[k],
-                                    dy=-dy_high,
-                                    head_length=0.3*dy_high,
-                                    **kwargs)
-        ax.add_patch(arrow)
 
 def get_swarm_spans(coll):
     """
@@ -147,6 +66,8 @@ def get_swarm_spans(coll):
     except ValueError:
         return None
 
+
+
 def gapped_lines(data, x, y,
                  type='mean_sd',
                  offset=0.3,

docs/Makefile

@@ -17,4 +17,4 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/source/_static/reticulate_tutorial.Rmd

@@ -0,0 +1,45 @@
+```{r}
+library(dplyr)
+library(ggplot2)
+
+df = filter(CO2, conc == '1000')
+
+ggplot(df, aes(x = Type, 
+               y = uptake, 
+               color = Treatment)) + 
+  geom_point() + 
+  ggtitle('CO2 conc = 1000 mL/L') + 
+  xlab('City') + ylab('CO2 uptake')
+```
+
+
+```{r}
+library(reticulate)
+```
+
+
+```{python}
+import matplotlib.pyplot as plt
+import dabest
+
+f1, results = dabest.plot(data=r.df, fig_size=(5,7),
+                         x='Type', y='uptake', 
+                         swarm_label='CO2 uptake',
+                         color_col='Treatment',
+                         idx=['Quebec', 'Mississippi']
+                         )
+
+f1.savefig('dabest-plot-CO2.png', bbox_inches='tight')
+```
+
+```{r}
+py_results = py$results
+mean_diff = py_results$stat_summary
+ci_low = py_results$bca_ci_low
+ci_high = py_results$bca_ci_high
+
+# Print results, with all numerical values formatted to 2 decimal places.
+sprintf("Mean Difference = %.2f [95CI %.2f, %.2f]", 
+        mean_diff, ci_low, ci_high)
+```
+

docs/source/_templates/layout.html

@@ -0,0 +1,15 @@
+{% extends "!layout.html" %}
+
+{%- block extrahead %}
+{{ super() }}
+<!-- Global site tag (gtag.js) - Google Analytics -->
+<script async src="https://www.googletagmanager.com/gtag/js?id=UA-120627927-1"></script>
+<script>
+  window.dataLayer = window.dataLayer || [];
+  function gtag(){dataLayer.push(arguments);}
+  gtag('js', new Date());
+
+  gtag('config', 'UA-120627927-1');
+</script>
+
+{% endblock %}

docs/source/conf.py

@@ -58,7 +58,7 @@
 # The short X.Y version.
 version = '0.1'
 # The full version, including alpha/beta/rc tags.
-release = '0.1.2'
+release = '0.1.3'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.