Merge pull request #9218 from bashtage/forward-port-doc-fixes

DOC: Fix multiple issues in notebooks

examples/notebooks/ets.ipynb

@@ -123,7 +123,7 @@
     "    549.8338,\n",
     "    542.3405,\n",
     "]\n",
-    "oil = pd.Series(oildata, index=pd.date_range(\"1965\", \"2013\", freq=\"AS\"))\n",
+    "oil = pd.Series(oildata, index=pd.date_range(\"1965\", \"2013\", freq=\"YS\"))\n",
     "oil.plot()\n",
     "plt.ylabel(\"Annual oil production in Saudi Arabia (Mt)\")"
    ]

examples/notebooks/exponential_smoothing.ipynb

@@ -54,7 +54,7 @@
     "    514.2689,\n",
     "    494.211,\n",
     "]\n",
-    "index = pd.date_range(start=\"1996\", end=\"2008\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1996\", end=\"2008\", freq=\"Y\")\n",
     "oildata = pd.Series(data, index)\n",
     "\n",
     "data = [\n",
@@ -74,7 +74,7 @@
     "    41.3864,\n",
     "    41.5966,\n",
     "]\n",
-    "index = pd.date_range(start=\"1990\", end=\"2005\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1990\", end=\"2005\", freq=\"Y\")\n",
     "air = pd.Series(data, index)\n",
     "\n",
     "data = [\n",
@@ -110,11 +110,11 @@
     "    408.2705,\n",
     "    414.2428,\n",
     "]\n",
-    "index = pd.date_range(start=\"1970\", end=\"2001\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1970\", end=\"2001\", freq=\"Y\")\n",
     "livestock2 = pd.Series(data, index)\n",
     "\n",
     "data = [407.9979, 403.4608, 413.8249, 428.105, 445.3387, 452.9942, 455.7402]\n",
-    "index = pd.date_range(start=\"2001\", end=\"2008\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"2001\", end=\"2008\", freq=\"Y\")\n",
     "livestock3 = pd.Series(data, index)\n",
     "\n",
     "data = [\n",

examples/notebooks/glm.ipynb

@@ -159,7 +159,7 @@
     "means75.iloc[0] = lowinc_75per = stats.scoreatpercentile(data.exog.iloc[:,0], 75)\n",
     "resp_25 = res.predict(means25)\n",
     "resp_75 = res.predict(means75)\n",
-    "diff = resp_75 - resp_25"
+    "diff = resp_75 - resp_25\n"
    ]
   },
   {
@@ -174,9 +174,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "print(\"%2.4f%%\" % (diff*100))"
-   ]
+   "source": "print(\"%2.4f%%\" % (diff.iloc[0]*100))"
   },
   {
    "cell_type": "markdown",

examples/notebooks/linear_regression_diagnostics_plots.ipynb

@@ -90,6 +90,7 @@
     "import matplotlib.pyplot as plt\n",
     "from typing import Type\n",
     "\n",
+    "style_talk = 'seaborn-talk'    #refer to plt.style.available\n",
     "\n",
     "class LinearRegDiagnostic():\n",
     "    \"\"\"\n",
@@ -155,7 +156,7 @@
     "        >>> df = pd.DataFrame({'x':x, 'y':y})\n",
     "        >>> res = smf.ols(formula= \"y ~ x\", data=df).fit()\n",
     "        >>> cls = Linear_Reg_Diagnostic(res)\n",
-    "        >>> cls(plot_context=\"seaborn-v0_8\")\n",
+    "        >>> cls(plot_context=\"seaborn-v0_8-paper\")\n",
     "\n",
     "        In case you do not need all plots you can also independently make an individual plot/table\n",
     "        in following ways\n",
@@ -186,7 +187,7 @@
     "        self.nparams = len(self.results.params)\n",
     "        self.nresids = len(self.residual_norm)\n",
     "\n",
-    "    def __call__(self, plot_context='seaborn-v0_8', **kwargs):\n",
+    "    def __call__(self, plot_context='seaborn-v0_8-paper', **kwargs):\n",
     "        # print(plt.style.available)\n",
     "        # GH#9157\n",
     "        if plot_context not in plt.style.available:\n",

examples/notebooks/markov_autoregression.ipynb

@@ -75,8 +75,21 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import requests\n",
+    "import shutil\n",
+    "\n",
+    "def download_file(url):\n",
+    "    local_filename = url.split('/')[-1]\n",
+    "    with requests.get(url, stream=True) as r:\n",
+    "        with open(local_filename, 'wb') as f:\n",
+    "            shutil.copyfileobj(r.raw, f)\n",
+    "\n",
+    "    return local_filename\n",
+    "\n",
+    "filename = download_file(\"https://www.stata-press.com/data/r14/rgnp.dta\")\n",
     "# Get the RGNP data to replicate Hamilton\n",
-    "dta = pd.read_stata(\"https://www.stata-press.com/data/r14/rgnp.dta\").iloc[1:]\n",
+    "\n",
+    "dta = pd.read_stata(filename).iloc[1:]\n",
     "dta.index = pd.DatetimeIndex(dta.date, freq=\"QS\")\n",
     "dta_hamilton = dta.rgnp\n",
     "\n",
@@ -283,7 +296,7 @@
     "std_ratio = (\n",
     "    dta_filardo[\"dlip\"][\"1960-01-01\":].std() / dta_filardo[\"dlip\"][:\"1959-12-01\"].std()\n",
     ")\n",
-    "dta_filardo[\"dlip\"][:\"1959-12-01\"] = dta_filardo[\"dlip\"][:\"1959-12-01\"] * std_ratio\n",
+    "dta_filardo.loc[:\"1959-12-01\", \"dlip\"] = dta_filardo[\"dlip\"][:\"1959-12-01\"] * std_ratio\n",
     "\n",
     "dta_filardo[\"dlleading\"] = np.log(dta_filardo[\"leading\"]).diff() * 100\n",
     "dta_filardo[\"dmdlleading\"] = dta_filardo[\"dlleading\"] - dta_filardo[\"dlleading\"].mean()\n",

examples/notebooks/recursive_ls.ipynb

@@ -47,7 +47,7 @@
     "print(sm.datasets.copper.DESCRLONG)\n",
     "\n",
     "dta = sm.datasets.copper.load_pandas().data\n",
-    "dta.index = pd.date_range(\"1951-01-01\", \"1975-01-01\", freq=\"AS\")\n",
+    "dta.index = pd.date_range(\"1951-01-01\", \"1975-01-01\", freq=\"YS\")\n",
     "endog = dta[\"WORLDCONSUMPTION\"]\n",
     "\n",
     "# To the regressors in the dataset, we add a column of ones for an intercept\n",

examples/notebooks/statespace_arma_0.ipynb

@@ -107,7 +107,7 @@
    },
    "outputs": [],
    "source": [
-    "dta.index = pd.Index(pd.date_range(\"1700\", end=\"2009\", freq=\"A-DEC\"))\n",
+    "dta.index = pd.Index(pd.date_range(\"1700\", end=\"2009\", freq=\"YE-DEC\"))\n",
     "del dta[\"YEAR\"]"
    ]
   },

examples/notebooks/statespace_forecasting.ipynb

@@ -595,7 +595,7 @@
    "outputs": [],
    "source": [
     "# Annual frequency, using a PeriodIndex\n",
-    "index = pd.period_range(start='2000', periods=4, freq='A')\n",
+    "index = pd.period_range(start='2000', periods=4, freq='Y')\n",
     "endog1 = pd.Series([1, 2, 3, 4], index=index)\n",
     "print(endog1.index)"
    ]
@@ -619,7 +619,7 @@
    "outputs": [],
    "source": [
     "# Monthly frequency, using a DatetimeIndex\n",
-    "index = pd.date_range(start='2000', periods=4, freq='M')\n",
+    "index = pd.date_range(start='2000', periods=4, freq='ME')\n",
     "endog3 = pd.Series([1, 2, 3, 4], index=index)\n",
     "print(endog3.index)"
    ]

examples/notebooks/statespace_local_linear_trend.ipynb

@@ -191,7 +191,7 @@
    "outputs": [],
    "source": [
     "# Load Dataset\n",
-    "df.index = pd.date_range(start='%d-01-01' % df.date[0], end='%d-01-01' % df.iloc[-1, 0], freq='AS')\n",
+    "df.index = pd.date_range(start='%d-01-01' % df.date[0], end='%d-01-01' % df.iloc[-1, 0], freq='YS')\n",
     "\n",
     "# Log transform\n",
     "df['lff'] = np.log(df['ff'])\n",

examples/notebooks/statespace_news.ipynb

@@ -503,7 +503,7 @@
     "infl.columns = ['PCE', 'CPI']\n",
     "\n",
     "# Remove two outliers and de-mean the series\n",
-    "infl['PCE'].loc['2001-09':'2001-10'] = np.nan"
+    "infl.loc['2001-09':'2001-10', 'PCE'] = np.nan"
    ]
   },
   {

examples/notebooks/statespace_varmax.ipynb

@@ -52,7 +52,20 @@
    },
    "outputs": [],
    "source": [
-    "dta = sm.datasets.webuse('lutkepohl2', 'https://www.stata-press.com/data/r12/')\n",
+    "import requests\n",
+    "import shutil \n",
+    "\n",
+    "def download_file(url):\n",
+    "    local_filename = url.split('/')[-1]\n",
+    "    with requests.get(url, stream=True) as r:\n",
+    "        with open(local_filename, 'wb') as f:\n",
+    "            shutil.copyfileobj(r.raw, f)\n",
+    "\n",
+    "    return local_filename\n",
+    "\n",
+    "filename = download_file(\"https://www.stata-press.com/data/r12/lutkepohl2.dta\")\n",
+    "\n",
+    "dta = pd.read_stata(filename)\n",
     "dta.index = dta.qtr\n",
     "dta.index.freq = dta.index.inferred_freq\n",
     "endog = dta.loc['1960-04-01':'1978-10-01', ['dln_inv', 'dln_inc', 'dln_consump']]"

examples/notebooks/tsa_dates.ipynb

@@ -66,7 +66,7 @@
    "source": [
     "from datetime import datetime\n",
     "\n",
-    "dates = pd.date_range(\"1700-1-1\", periods=len(data.endog), freq=\"A-DEC\")"
+    "dates = pd.date_range(\"1700-1-1\", periods=len(data.endog), freq=\"YE-DEC\")"
    ]
   },
   {