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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
|
Description: Use cached datasets in tests and examples
Also remove a download that isn't actually used in that example.
This allows the tests to pass, and at least some of the examples to
be built, in an offline environment such as a Debian buildd.
The cached data is extracted from R packages by debian/datasets/*.
Author: Diane Trout <[email protected]>, Rebecca N. Palmer <[email protected]>
Forwarded: not-needed
--- a/docs/source/contingency_tables.rst
b/docs/source/contingency_tables.rst
@@ -49,7 49,7 @@ contingency table cell counts:
import pandas as pd
import statsmodels.api as sm
- df = sm.datasets.get_rdataset("Arthritis", "vcd").data
df = sm.datasets.get_rdataset("Arthritis", "vcd", cache=True).data
tab = pd.crosstab(df['Treatment'], df['Improved'])
tab = tab.loc[:, ["None", "Some", "Marked"]]
@@ -184,7 184,7 @@ contingency table.
.. ipython:: python
- df = sm.datasets.get_rdataset("VisualAcuity", "vcd").data
df = sm.datasets.get_rdataset("VisualAcuity", "vcd", cache=True).data
df = df.loc[df.gender == "female", :]
tab = df.set_index(['left', 'right'])
del tab["gender"]
--- a/docs/source/duration.rst
b/docs/source/duration.rst
@@ -41,7 41,7 @@ We fit the survival distribution only fo
import statsmodels.api as sm
- data = sm.datasets.get_rdataset("flchain", "survival").data
data = sm.datasets.get_rdataset("flchain", "survival", cache=True).data
df = data.loc[data.sex == "F", :]
sf = sm.SurvfuncRight(df["futime"], df["death"])
@@ -152,7 152,7 @@ depending on the value of the covariates
import statsmodels.api as sm
import statsmodels.formula.api as smf
- data = sm.datasets.get_rdataset("flchain", "survival").data
data = sm.datasets.get_rdataset("flchain", "survival", cache=True).data
del data["chapter"]
data = data.dropna()
data["lam"] = data["lambda"]
--- a/docs/source/example_formulas.rst
b/docs/source/example_formulas.rst
@@ -47,7 47,7 @@ and list-wise delete to remove missing o
.. ipython:: python
- df = sm.datasets.get_rdataset("Guerry", "HistData").data
df = sm.datasets.get_rdataset("Guerry", "HistData", cache=True).data
df = df[['Lottery', 'Literacy', 'Wealth', 'Region']].dropna()
df.head()
--- a/docs/source/gee.rst
b/docs/source/gee.rst
@@ -24,7 24,7 @@ within clusters using data on epilepsy s
import statsmodels.api as sm
import statsmodels.formula.api as smf
- data = sm.datasets.get_rdataset('epil', package='MASS').data
data = sm.datasets.get_rdataset('epil', package='MASS', cache=True).data
fam = sm.families.Poisson()
ind = sm.cov_struct.Exchangeable()
--- a/docs/source/gettingstarted.rst
b/docs/source/gettingstarted.rst
@@ -50,7 50,7 @@ We could download the file locally and t
.. ipython:: python
- df = sm.datasets.get_rdataset("Guerry", "HistData").data
df = sm.datasets.get_rdataset("Guerry", "HistData", cache=True).data
The `Input/Output doc page <iolib.html>`_ shows how to import from various
other formats.
--- a/docs/source/index.rst
b/docs/source/index.rst
@@ -23,7 23,7 @@ Here is a simple example using ordinary
import statsmodels.formula.api as smf
# Load data
- dat = sm.datasets.get_rdataset("Guerry", "HistData").data
dat = sm.datasets.get_rdataset("Guerry", "HistData", cache=True).data
# Fit regression model (using the natural log of one of the regressors)
results = smf.ols('Lottery ~ Literacy np.log(Pop1831)', data=dat).fit()
--- a/docs/source/mixed_linear.rst
b/docs/source/mixed_linear.rst
@@ -83,7 83,7 @@ Examples
import statsmodels.api as sm
import statsmodels.formula.api as smf
- data = sm.datasets.get_rdataset("dietox", "geepack").data
data = sm.datasets.get_rdataset("dietox", "geepack", cache=True).data
md = smf.mixedlm("Weight ~ Time", data, groups=data["Pig"])
mdf = md.fit()
--- a/docs/source/release/version0.6.rst
b/docs/source/release/version0.6.rst
@@ -41,7 41,7 @@ covariates.
import statsmodels.api as sm
import statsmodels.formula.api as smf
- data = sm.datasets.get_rdataset("epil", "MASS").data
data = sm.datasets.get_rdataset("epil", "MASS", cache=True).data
md = smf.gee("y ~ age trt base", "subject", data,
cov_struct=sm.cov_struct.Independence(),
--- a/docs/source/datasets/index.rst
b/docs/source/datasets/index.rst
@@ -30,7 30,7 @@ The `Rdatasets project <https://vincenta
.. ipython:: python
import statsmodels.api as sm
- duncan_prestige = sm.datasets.get_rdataset("Duncan", "carData")
duncan_prestige = sm.datasets.get_rdataset("Duncan", "carData", cache=True)
print(duncan_prestige.__doc__)
duncan_prestige.data.head(5)
--- a/examples/notebooks/markov_regression.ipynb
b/examples/notebooks/markov_regression.ipynb
@@ -28,11 28,7 @@
"import pandas as pd\n",
"import statsmodels.api as sm\n",
"import matplotlib.pyplot as plt\n",
- "\n",
- "# NBER recessions\n",
- "from pandas_datareader.data import DataReader\n",
- "from datetime import datetime\n",
- "usrec = DataReader('USREC', 'fred', start=datetime(1947, 1, 1), end=datetime(2013, 4, 1))"
"from datetime import datetime\n"
]
},
{
--- a/examples/notebooks/mixed_lm_example.ipynb
b/examples/notebooks/mixed_lm_example.ipynb
@@ -86,7 86,7 @@
"metadata": {},
"outputs": [],
"source": [
- "data = sm.datasets.get_rdataset('dietox', 'geepack').data\n",
"data = sm.datasets.get_rdataset('dietox', 'geepack', cache=True).data\n",
"md = smf.mixedlm(\"Weight ~ Time\", data, groups=data[\"Pig\"])\n",
"mdf = md.fit(method=[\"lbfgs\"])\n",
"print(mdf.summary())"
@@ -318,7 318,7 @@
"metadata": {},
"outputs": [],
"source": [
- "data = sm.datasets.get_rdataset(\"Sitka\", \"MASS\").data\n",
"data = sm.datasets.get_rdataset(\"Sitka\", \"MASS\", cache=True).data\n",
"endog = data[\"size\"]\n",
"data[\"Intercept\"] = 1\n",
"exog = data[[\"Intercept\", \"Time\"]]"
--- a/examples/notebooks/regression_diagnostics.ipynb
b/examples/notebooks/regression_diagnostics.ipynb
@@ -47,8 47,8 @@
"import matplotlib.pyplot as plt\n",
"\n",
"# Load data\n",
- "url = 'https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/HistData/Guerry.csv'\n",
- "dat = pd.read_csv(url)\n",
"import statsmodels.datasets\n",
"dat = statsmodels.datasets.get_rdataset(\"Guerry\", \"HistData\", cache=True).data\n",
"\n",
"# Fit regression model (using the natural log of one of the regressors)\n",
"results = smf.ols('Lottery ~ Literacy np.log(Pop1831)', data=dat).fit()\n",
--- a/statsmodels/stats/tests/test_dist_dependant_measures.py
b/statsmodels/stats/tests/test_dist_dependant_measures.py
@@ -137,7 137,7 @@ class TestDistDependenceMeasures(object)
0.1025087
"""
try:
- iris = get_rdataset("iris").data.values[:, :4]
iris = get_rdataset("iris", cache=True).data.values[:, :4]
except IGNORED_EXCEPTIONS:
pytest.skip('Failed with HTTPError or URLError, these are random')
@@ -177,7 177,7 @@ class TestDistDependenceMeasures(object)
30.01526
"""
try:
- quakes = get_rdataset("quakes").data.values[:, :3]
quakes = get_rdataset("quakes", cache=True).data.values[:, :3]
except IGNORED_EXCEPTIONS:
pytest.skip('Failed with HTTPError or URLError, these are random')
|