Use cached datasets for building documentation/examples

Also remove a download that isn't actually used in that example.

This allows 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 <diane@ghic.org>, Rebecca N. Palmer <rebecca_palmer@zoho.com>
Forwarded: not-needed

Gbp-Pq: Name use-cached-datasets

diff --git a/docs/source/contingency_tables.rst b/docs/source/contingency_tables.rst
index a4927eb34434679315e723feb8738c26b3f43cdd..cf66652e303a7c1fbcec528715b7bc546a59fba3 100644 (file)
--- 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"]

diff --git a/docs/source/datasets/index.rst b/docs/source/datasets/index.rst
index 92cefb0f7c7ddc976898b3ac4b3bbcf906a2fc42..f66dae48bbd3371cfd2654c533facb9a40bfd9b9 100644 (file)
--- a/docs/source/datasets/index.rst
+++ b/docs/source/datasets/index.rst
@@ -30,7 +30,7 @@ The `Rdatasets project <https://vincentarelbundock.github.io/Rdatasets/>`__ give
 .. 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)
 

diff --git a/docs/source/duration.rst b/docs/source/duration.rst
index 66ae9a231d297e6feb5aaa1af6c5ec45f005dcba..f861f9747bdd121d10eefccbea04a52bd11826d3 100644 (file)
--- a/docs/source/duration.rst
+++ b/docs/source/duration.rst
@@ -44,7 +44,7 @@ We fit the survival distribution only for the female subjects.
 
    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"])
 
@@ -157,7 +157,7 @@ Examples
    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"]

diff --git a/docs/source/example_formulas.rst b/docs/source/example_formulas.rst
index 027599437950575c9e3806ccc68fccddfbd40c70..b950e4d6058003b9d0d1f666df35872e942eff1d 100644 (file)
--- a/docs/source/example_formulas.rst
+++ b/docs/source/example_formulas.rst
@@ -47,7 +47,7 @@ and list-wise delete to remove missing observations:
 
 .. 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()
 

diff --git a/docs/source/gee.rst b/docs/source/gee.rst
index bf45eb70c39a77ff6c9f07d9014d41a93d1896ef..b06326c6cc02a11f17f4c8e392e2e6ecd65c821d 100644 (file)
--- a/docs/source/gee.rst
+++ b/docs/source/gee.rst
@@ -24,7 +24,7 @@ within clusters using data on epilepsy seizures.
     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()

diff --git a/docs/source/gettingstarted.rst b/docs/source/gettingstarted.rst
index e62a1b418cb3e50cd7d7fe243c04e32a181b3f5d..ff27ab63edca51a1100f5cacfaf7bffe0e932bc3 100644 (file)
--- a/docs/source/gettingstarted.rst
+++ b/docs/source/gettingstarted.rst
@@ -44,7 +44,7 @@ We could download the file locally and then load it using ``read_csv``, but
 
 .. 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.

diff --git a/docs/source/index.rst b/docs/source/index.rst
index d75da986dcde3b768fb7a07595cdc3af456e8c3a..01b017051e3d9f35a7db63bf9dff08bf7e7e4faf 100644 (file)
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -25,7 +25,7 @@ example using ordinary least squares:
     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()

diff --git a/docs/source/mixed_linear.rst b/docs/source/mixed_linear.rst
index 4e50a40d5592acf854ee2a7b2353b6626a5bb758..ef3d1f0f3d3341743575a2745ccd97b4e5406cc7 100644 (file)
--- 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()

diff --git a/docs/source/release/version0.6.rst b/docs/source/release/version0.6.rst
index 53eda464ffff4929a5affcba458ac2709bfb247f..e735b0170a571f433f70c49ff4f96c0886dcc53c 100644 (file)
--- 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(), 

diff --git a/examples/notebooks/markov_regression.ipynb b/examples/notebooks/markov_regression.ipynb
index 135778345403daa79d21fde770e110c9239c97ee..357724add8dae5920746a79de739c6cc83e653ff 100644 (file)
--- 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"
    ]
   },
   {

diff --git a/examples/notebooks/mixed_lm_example.ipynb b/examples/notebooks/mixed_lm_example.ipynb
index 6f40219545d813eecb6f10a2e5ad4f93c6438f0a..7084d748c72b1975c028cd4c532be46232cfc434 100644 (file)
--- a/examples/notebooks/mixed_lm_example.ipynb
+++ b/examples/notebooks/mixed_lm_example.ipynb
@@ -68,7 +68,7 @@
    "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()\n",
     "print(mdf.summary())"
@@ -202,7 +202,7 @@
    "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\"]]"

diff --git a/examples/notebooks/regression_diagnostics.ipynb b/examples/notebooks/regression_diagnostics.ipynb
index 140eafcedba88c871c5991d88d9700f205ae654d..df7f6e85cbf0f027f24ab25df679be38f4cd1951 100644 (file)
--- a/examples/notebooks/regression_diagnostics.ipynb
+++ b/examples/notebooks/regression_diagnostics.ipynb
@@ -52,8 +52,8 @@
     "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",