Starting refactoring phase 2

Author: cyberosa

.github/workflows/test-pytest.yaml

@@ -15,4 +15,4 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install -e '.[dev]'
-          pytest nbs/tests/ --mpl --mpl-baseline-path=nbs/tests/baseline_images
+          pytest nbs/tests/ --mpl --mpl-baseline-path=nbs/tests/mpl_image_tests/baseline_images

dabest/_dabest_object.py

@@ -61,7 +61,7 @@ def __init__(
                 err0 = "`proportional` and `mini_meta` cannot be True at the same time."
                 raise ValueError(err0)
             if self.__delta2:
-                err0 = "`delta` and `mini_meta` cannot be True at the same time."
+                err0 = "`delta2` and `mini_meta` cannot be True at the same time."
                 raise ValueError(err0)
 
             # Check if the columns stated are valid
@@ -86,8 +86,12 @@ def __init__(
         # Create experiment_label and x1_level
         if self.__delta2:
             # TODO Wrap the errors in a separate function called check_errors()
+            if x is None:
+                error_msg = "If `delta2` is True. `x` parameter cannot be None. String or list expected"
+                raise ValueError(error_msg)
+                
             if self.__proportional:
-                err0 = "`proportional` and `delta` cannot be True at the same time."
+                err0 = "`proportional` and `delta2` cannot be True at the same time."
                 raise ValueError(err0)
 
             # idx should not be specified

nbs/API/dabest_object.ipynb

@@ -130,7 +130,7 @@
     "                err0 = \"`proportional` and `mini_meta` cannot be True at the same time.\"\n",
     "                raise ValueError(err0)\n",
     "            if self.__delta2:\n",
-    "                err0 = \"`delta` and `mini_meta` cannot be True at the same time.\"\n",
+    "                err0 = \"`delta2` and `mini_meta` cannot be True at the same time.\"\n",
     "                raise ValueError(err0)\n",
     "\n",
     "            # Check if the columns stated are valid\n",
@@ -155,8 +155,12 @@
     "        # Create experiment_label and x1_level\n",
     "        if self.__delta2:\n",
     "            # TODO Wrap the errors in a separate function called check_errors()\n",
+    "            if x is None:\n",
+    "                error_msg = \"If `delta2` is True. `x` parameter cannot be None. String or list expected\"\n",
+    "                raise ValueError(error_msg)\n",
+    "                \n",
     "            if self.__proportional:\n",
-    "                err0 = \"`proportional` and `delta` cannot be True at the same time.\"\n",
+    "                err0 = \"`proportional` and `delta2` cannot be True at the same time.\"\n",
     "                raise ValueError(err0)\n",
     "\n",
     "            # idx should not be specified\n",

nbs/pytest.ini

@@ -3,7 +3,7 @@ filterwarnings =
     ignore::UserWarning
     ignore::DeprecationWarning
 
-addopts = --mpl --mpl-baseline-path=nbs/tests/baseline_images
+addopts = --mpl --mpl-baseline-path=nbs/tests/mpl_image_tests/baseline_images
 
 markers =
     mpl_image_compare: mark a test as implementing mpl image comparison.

nbs/tests/README.md

@@ -0,0 +1,70 @@
+import pandas as pd
+import numpy as np
+
+# Data for tests.
+# See Cumming, G. Understanding the New Statistics:
+# Effect Sizes, Confidence Intervals, and Meta-Analysis. Routledge, 2012,
+# from Cumming 2012 Table 11.1 Pg 287.
+wb = {
+    "control": [34, 54, 33, 44, 45, 53, 37, 26, 38, 58],
+    "expt": [66, 38, 35, 55, 48, 39, 65, 32, 57, 41],
+}
+wellbeing = pd.DataFrame(wb)
+
+
+# from Cumming 2012 Table 11.2 Page 291
+paired_wb = {
+    "pre": [43, 28, 54, 36, 31, 48, 50, 69, 29, 40],
+    "post": [51, 33, 58, 42, 39, 45, 54, 68, 35, 44],
+    "ID": np.arange(10),
+}
+paired_wellbeing = pd.DataFrame(paired_wb)
+
+
+# Data for testing Cohen's calculation.
+# Only work with binary data.
+# See Venables, W. N. and Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth edition. Springer.
+# Make two groups of `smoke` by choosing `low` as a standard, and the data is trimed from the back.
+
+# to remove the array wrapping behaviour of black
+# fmt: off
+sk = {  "low":  [0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1,
+                 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0],
+        "high": [1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0,
+                 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1]}
+# fmt: on
+smoke = pd.DataFrame(sk)
+
+
+# Data from Hogarty and Kromrey (1999)
+# Kromrey, Jeffrey D., and Kristine Y. Hogarty. 1998.
+# "Analysis Options for Testing Group Differences on Ordered Categorical
+# Variables: An Empirical Investigation of Type I Error Control
+# Statistical Power."
+# Multiple Linear Regression Viewpoints 25 (1): 70 - 82.
+likert_control = [1, 1, 2, 2, 2, 3, 3, 3, 4, 5]
+likert_treatment = [1, 2, 3, 4, 4, 5]
+
+
+# Data from Cliff (1993)
+# Cliff, Norman. 1993. "Dominance Statistics: Ordinal Analyses to Answer
+# Ordinal Questions."
+# Psychological Bulletin 114 (3): 494-509.
+a_scores = [6, 7, 9, 10]
+b_scores = [1, 3, 4, 7, 8]
+
+
+# kwargs for Dabest class init.
+dabest_default_kwargs = dict(
+    x=None,
+    y=None,
+    ci=95,
+    resamples=5000,
+    random_seed=12345,
+    proportional=False,
+    delta2=False,
+    experiment=None,
+    experiment_label=None,
+    x1_level=None,
+    mini_meta=False,
+)

nbs/tests/data/mocked_data_test_01.py

@@ -0,0 +1,34 @@
+import pandas as pd
+import numpy as np
+
+# Data for tests
+# See Der, G., & Everitt, B. S. (2009). A handbook
+# of statistical analyses using SAS, from Display 11.1
+
+# to remove the array wrapping behaviour of black
+# fmt: off
+group = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+         2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]
+first = [20, 14, 7, 6, 9, 9, 7, 18, 6, 10, 5, 11, 10, 17, 16, 7, 5, 16, 2, 7, 9, 2, 7, 19,
+         7, 9, 6, 13, 9, 6, 11, 7, 8, 3, 4, 11, 1, 6, 0, 18, 15, 10,  6,  9,  4,  4, 10]
+second = [15, 12, 5, 10, 7, 9, 3, 17, 9, 15, 9, 11, 2, 12, 15, 10, 0, 7, 1, 11, 16,
+        5, 3, 13, 5, 12, 7, 18, 10, 7, 11, 10, 18, 3, 10, 10, 3, 7, 3, 18, 15, 14, 6, 9, 3, 13, 11]
+third = [14, 12, 5, 9, 9, 9, 7, 16, 9, 12, 7, 8, 9, 14, 12, 4, 5, 7, 1, 7, 14, 6, 5, 14, 8, 16, 10,
+         14, 12, 8, 12, 11, 19, 3, 11, 10, 2, 7, 3, 19, 15, 16, 7, 13, 4, 13, 13]
+fourth = [13, 10, 6, 8, 5, 11, 6, 14, 9, 12, 3, 8, 3, 10, 7, 7, 0, 6, 2, 5, 10, 7, 5, 12, 8, 17, 15,
+          21, 14, 9, 14, 12, 19, 7, 17, 15, 4, 9, 4, 22, 18, 17, 9, 16, 7, 16, 17]
+fifth = [13, 10, 5, 7, 4, 8, 5, 12, 9, 11, 5, 9, 5, 9, 9, 5, 0, 4, 2, 8, 6, 6, 5, 10, 6, 18, 16, 21,
+         15, 12, 16, 14, 22, 8, 18, 16, 5, 10, 6, 22, 19, 19, 10, 20, 9, 19, 21]
+# fmt: on
+
+df = pd.DataFrame(
+    {
+        "Group": group,
+        "First": first,
+        "Second": second,
+        "Third": third,
+        "Fourth": fourth,
+        "Fifth": fifth,
+        "ID": np.arange(0, 47),
+    }
+)

nbs/tests/data/mocked_data_test_04.py

@@ -0,0 +1,9 @@
+import pandas as pd
+import scipy as sp
+from numpy import random
+
+random.seed(88888)
+N = 10
+c1 = sp.stats.norm.rvs(loc=100, scale=5, size=N)
+t1 = sp.stats.norm.rvs(loc=115, scale=5, size=N)
+dummy_df = pd.DataFrame({"Control 1": c1, "Test 1": t1})