Merge pull request #119 from LI-Yixuan/delta-delta

Delta delta

Author: josesho

.gitignore

@@ -122,3 +122,7 @@ fontList-v300.json
 # tex folders
 tex.cache/
 .Rproj.user
+testtt.py
+real.py
+0to2_beforeduringafter.csv
+

dabest/__init__.py

@@ -23,4 +23,4 @@
 from ._stats_tools import effsize as effsize
 from ._classes import TwoGroupsEffectSize, PermutationTest
 
-__version__ = "0.3.1"
+__version__ = "0.3.9999"

dabest/_api.py

@@ -4,8 +4,10 @@
 # Email : joseshowh@gmail.com
 
 
-def load(data, idx, x=None, y=None, paired=False, id_col=None,
-        ci=95, resamples=5000, random_seed=12345):
+def load(data, idx=None, x=None, y=None, paired=None, id_col=None,
+        ci=95, resamples=5000, random_seed=12345, proportional=False, 
+        delta2 = False, experiment = None, experiment_label = None,
+        x1_level = None):
     '''
     Loads data in preparation for estimation statistics.
 
@@ -18,10 +20,14 @@ def load(data, idx, x=None, y=None, paired=False, id_col=None,
         List of column names (if 'x' is not supplied) or of category names
         (if 'x' is supplied). This can be expressed as a tuple of tuples,
         with each individual tuple producing its own contrast plot
-    x : string, default None
+    x : string or list, default None
+        Column name(s) of the independent variable. This can be expressed as
+        a list of 2 elements if and only if 'delta2' is True; otherwise it 
+        can only be a string.
     y : string, default None
         Column names for data to be plotted on the x-axis and y-axis.
-    paired : boolean, default False.
+    paired : string, default None
+        The type of the experiment under which the data are obtained
     id_col : default None.
         Required if `paired` is True.
     ci : integer, default 95
@@ -34,6 +40,21 @@ def load(data, idx, x=None, y=None, paired=False, id_col=None,
         This integer is used to seed the random number generator during
         bootstrap resampling, ensuring that the confidence intervals
         reported are replicable.
+    proportional : boolean, default False. 
+        TO INCLUDE MORE DESCRIPTION ABOUT DATA FORMAT
+    delta2 : boolean, default False
+        Indicator of delta-delta experiment
+    experiment : String, default None
+        The name of the column of the dataframe which contains the label of 
+        experiments
+    experiment_lab : list, default None
+        A list of String to specify the order of subplots for delta-delta plots.
+        This can be expressed as a list of 2 elements if and only if 'delta2' 
+        is True; otherwise it can only be a string. 
+    x1_level : list, default None
+        A list of String to specify the order of subplots for delta-delta plots.
+        This can be expressed as a list of 2 elements if and only if 'delta2' 
+        is True; otherwise it can only be a string. 
 
     Returns
     -------
@@ -62,4 +83,4 @@ def load(data, idx, x=None, y=None, paired=False, id_col=None,
     '''
     from ._classes import Dabest
 
-    return Dabest(data, idx, x, y, paired, id_col, ci, resamples, random_seed)
+    return Dabest(data, idx, x, y, paired, id_col, ci, resamples, random_seed, proportional, delta2, experiment, experiment_label, x1_level)

dabest/_bootstrap_tools.py

@@ -9,92 +9,70 @@
 
 class bootstrap:
     '''Computes the summary statistic and a bootstrapped confidence interval.
-
     Keywords:
         x1, x2: array-like
             The data in a one-dimensional array form. Only x1 is required.
             If x2 is given, the bootstrapped summary difference between
             the two groups (x2-x1) is computed.
             NaNs are automatically discarded.
-
         paired: boolean, default False
             Whether or not x1 and x2 are paired samples.
-
         statfunction: callable, default np.mean
             The summary statistic called on data.
-
         smoothboot: boolean, default False
             Taken from seaborn.algorithms.bootstrap.
             If True, performs a smoothed bootstrap (draws samples from a kernel
             destiny estimate).
-
         alpha: float, default 0.05
             Denotes the likelihood that the confidence interval produced
             does not include the true summary statistic. When alpha = 0.05,
             a 95% confidence interval is produced.
-
         reps: int, default 5000
             Number of bootstrap iterations to perform.
-
     Returns:
         An `bootstrap` object reporting the summary statistics, percentile CIs,
         bias-corrected and accelerated (BCa) CIs, and the settings used.
-
         summary: float
             The summary statistic.
-
         is_difference: boolean
             Whether or not the summary is the difference between two groups.
             If False, only x1 was supplied.
-
         is_paired: boolean
             Whether or not the difference reported is between 2 paired groups.
-
         statistic: callable
             The function used to compute the summary.
-
         reps: int
             The number of bootstrap iterations performed.
-
         stat_array: array.
             A sorted array of values obtained by bootstrapping the input arrays.
-
         ci: float
             The size of the confidence interval reported (in percentage).
-
         pct_ci_low, pct_ci_high: floats
             The upper and lower bounds of the confidence interval as computed
             by taking the percentage bounds.
-
         pct_low_high_indices: array
             An array with the indices in `stat_array` corresponding to the
             percentage confidence interval bounds.
-
         bca_ci_low, bca_ci_high: floats
             The upper and lower bounds of the bias-corrected and accelerated
             (BCa) confidence interval. See Efron 1977.
-
         bca_low_high_indices: array
             An array with the indices in `stat_array` corresponding to the BCa
             confidence interval bounds.
-
         pvalue_1samp_ttest: float
             P-value obtained from scipy.stats.ttest_1samp. If 2 arrays were
             passed (x1 and x2), returns 'NIL'.
             See https://docs.scipy.org/doc/scipy-1.0.0/reference/generated/scipy.stats.ttest_1samp.html
-
         pvalue_2samp_ind_ttest: float
             P-value obtained from scipy.stats.ttest_ind.
             If a single array was given (x1 only), or if `paired` is True,
             returns 'NIL'.
             See https://docs.scipy.org/doc/scipy-1.0.0/reference/generated/scipy.stats.ttest_ind.html
-
         pvalue_2samp_related_ttest: float
             P-value obtained from scipy.stats.ttest_rel.
             If a single array was given (x1 only), or if `paired` is False,
             returns 'NIL'.
             See https://docs.scipy.org/doc/scipy-1.0.0/reference/generated/scipy.stats.ttest_rel.html
-
         pvalue_wilcoxon: float
             P-value obtained from scipy.stats.wilcoxon.
             If a single array was given (x1 only), or if `paired` is False,
@@ -103,14 +81,12 @@ class bootstrap:
             the null hypothesis that the related samples x1 and x2 are from
             the same distribution.
             See https://docs.scipy.org/doc/scipy-1.0.0/reference/scipy.stats.wilcoxon.html
-
         pvalue_mann_whitney: float
             Two-sided p-value obtained from scipy.stats.mannwhitneyu.
             If a single array was given (x1 only), returns 'NIL'.
             The Mann-Whitney U-test is a nonparametric unpaired test of the null
             hypothesis that x1 and x2 are from the same distribution.
             See https://docs.scipy.org/doc/scipy-1.0.0/reference/generated/scipy.stats.mannwhitneyu.html
-
     '''
     def __init__(self, x1, x2=None,
         paired=False,
@@ -284,7 +260,6 @@ def jackknife_indexes(data):
     From the scikits.bootstrap package.
     Given an array, returns a list of arrays where each array is a set of
     jackknife indexes.
-
     For a given set of data Y, the jackknife sample J[i] is defined as the
     data set Y with the ith data point deleted.
     """
@@ -332,4 +307,4 @@ def bca(data, alphas, statarray, statfunction, ostat, reps):
     nvals = np.round((reps-1)*avals)
     nvals = np.nan_to_num(nvals).astype('int')
 
-    return nvals
+    return nvals