1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
Description: Use fixed seeds for reproducible pseudorandomness
Author: Rebecca N. Palmer <rebecca_palmer@zoho.com>
Forwarded: no
--- a/doc/source/getting_started/comparison/comparison_with_r.rst
+++ b/doc/source/getting_started/comparison/comparison_with_r.rst
@@ -237,6 +237,7 @@ In pandas we may use :meth:`~pandas.pivo
import random
import string
+ random.seed(123456) # for reproducibility
baseball = pd.DataFrame(
{
--- a/doc/source/user_guide/advanced.rst
+++ b/doc/source/user_guide/advanced.rst
@@ -590,6 +590,7 @@ they need to be sorted. As with any inde
import random
+ random.seed(123456) # for reproducibility
random.shuffle(tuples)
s = pd.Series(np.random.randn(8), index=pd.MultiIndex.from_tuples(tuples))
s
--- a/doc/source/user_guide/visualization.rst
+++ b/doc/source/user_guide/visualization.rst
@@ -1086,6 +1086,7 @@ are what constitutes the bootstrap plot.
:suppress:
np.random.seed(123456)
+ random.seed(123456) # for reproducibility - bootstrap_plot uses random.sample
.. ipython:: python
--- a/pandas/plotting/_core.py
+++ b/pandas/plotting/_core.py
@@ -604,6 +604,7 @@ def boxplot_frame_groupby(
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
>>> import itertools
>>> tuples = [t for t in itertools.product(range(1000), range(4))]
>>> index = pd.MultiIndex.from_tuples(tuples, names=['lvl0', 'lvl1'])
@@ -1328,6 +1329,7 @@ class PlotAccessor(PandasObject):
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
>>> data = np.random.randn(25, 4)
>>> df = pd.DataFrame(data, columns=list('ABCD'))
>>> ax = df.plot.box()
@@ -1392,6 +1394,7 @@ class PlotAccessor(PandasObject):
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
>>> df = pd.DataFrame(np.random.randint(1, 7, 6000), columns=['one'])
>>> df['two'] = df['one'] + np.random.randint(1, 7, 6000)
>>> ax = df.plot.hist(bins=12, alpha=0.5)
@@ -1811,6 +1814,7 @@ class PlotAccessor(PandasObject):
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
>>> n = 10000
>>> df = pd.DataFrame({'x': np.random.randn(n),
... 'y': np.random.randn(n)})
--- a/pandas/plotting/_misc.py
+++ b/pandas/plotting/_misc.py
@@ -438,6 +438,8 @@ def bootstrap_plot(
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
+ >>> random.seed(1234) # for reproducibility
>>> s = pd.Series(np.random.uniform(size=100))
>>> pd.plotting.bootstrap_plot(s) # doctest: +SKIP
<Figure size 640x480 with 6 Axes>
@@ -597,6 +599,7 @@ def autocorrelation_plot(series: Series,
.. plot::
:context: close-figs
+ >>> np.random.seed(1234)
>>> spacing = np.linspace(-9 * np.pi, 9 * np.pi, num=1000)
>>> s = pd.Series(0.7 * np.random.rand(1000) + 0.3 * np.sin(spacing))
>>> pd.plotting.autocorrelation_plot(s) # doctest: +SKIP
--- a/doc/source/user_guide/style.ipynb
+++ b/doc/source/user_guide/style.ipynb
@@ -78,8 +78,37 @@
"source": [
"import pandas as pd\n",
"import numpy as np\n",
- "import matplotlib as mpl\n",
- "\n",
+ "import matplotlib as mpl\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "nbsphinx": "hidden"
+ },
+ "outputs": [],
+ "source": [
+ "# For reproducibility - this doesn't respect uuid_len or positionally-passed uuid but the places here that use that coincidentally bypass this anyway\n",
+ "from pandas.io.formats.style import Styler\n",
+ "next_uuid = 1000\n",
+ "class StylerReproducible(Styler):\n",
+ " def __init__(self, *args, uuid=None, **kwargs):\n",
+ " global next_uuid\n",
+ " if uuid is None:\n",
+ " uuid = str(next_uuid)\n",
+ " next_uuid = next_uuid + 1\n",
+ " super().__init__(*args, uuid=uuid, **kwargs)\n",
+ "Styler = StylerReproducible\n",
+ "pd.DataFrame.style = property(lambda self: StylerReproducible(self))\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
"df = pd.DataFrame({\n",
" \"strings\": [\"Adam\", \"Mike\"],\n",
" \"ints\": [1, 3],\n",
@@ -104,6 +133,7 @@
"metadata": {},
"outputs": [],
"source": [
+ "np.random.seed(25) # for reproducibility\n",
"weather_df = pd.DataFrame(np.random.rand(10,2)*5, \n",
" index=pd.date_range(start=\"2021-01-01\", periods=10),\n",
" columns=[\"Tokyo\", \"Beijing\"])\n",
@@ -1394,7 +1424,6 @@
"outputs": [],
"source": [
"# Hide the construction of the display chart from the user\n",
- "import pandas as pd\n",
"from IPython.display import HTML\n",
"\n",
"# Test series\n",
@@ -1926,6 +1955,18 @@
]
},
{
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "nbsphinx": "hidden"
+ },
+ "outputs": [],
+ "source": [
+ "# For reproducibility\n",
+ "Styler = StylerReproducible\n"
+ ]
+ },
+ {
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -2126,7 +2167,8 @@
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.5"
- }
+ },
+ "record_timing": false
},
"nbformat": 4,
"nbformat_minor": 1
|
