Documentation update for not failing with constant extra regressor

docs/_docs/diagnostics.md

@@ -221,4 +221,4 @@ fig = plot_cross_validation_metric(df_cv, metric='mape')
 
 The size of the rolling window in the figure can be changed with the optional argument `rolling_window`, which specifies the proportion of forecasts to use in each rolling window. The default is 0.1, corresponding to 10% of rows from `df_cv` included in each window; increasing this will lead to a smoother average curve in the figure.
 
-When using cross validation on a model with extra regressors, the cross validation will exit with an error if the extra regressor is constant in the simulated history. The `initial` period should be long enough for the extra regressor to take on multiple values. Similarly, the initial period should be long enough to capture any seasonalities that are included in the model: at least a year for yearly seasonality, at least a week for weekly seasonality, etc.
+The `initial` period should be long enough to capture all of the components of the model, in particular seasonalities and extra regressors: at least a year for yearly seasonality, at least a week for weekly seasonality, etc.

docs/_docs/seasonality,_holiday_effects,_and_regressors.md

@@ -427,7 +427,7 @@ fig = m.plot_components(forecast)
 ![png](/prophet/static/seasonality,_holiday_effects,_and_regressors_files/seasonality,_holiday_effects,_and_regressors_32_0.png) 
 
 
-NFL Sundays could also have been handled using the "holidays" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known. The regressor cannot be constant in the training data; fitting will exit with an error if it is.
+NFL Sundays could also have been handled using the "holidays" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known.
 
 The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R. Note that regressors must be added prior to model fitting.
 

notebooks/diagnostics.ipynb

@@ -476,7 +476,7 @@
    "source": [
     "The size of the rolling window in the figure can be changed with the optional argument `rolling_window`, which specifies the proportion of forecasts to use in each rolling window. The default is 0.1, corresponding to 10% of rows from `df_cv` included in each window; increasing this will lead to a smoother average curve in the figure.\n",
     "\n",
-    "When using cross validation on a model with extra regressors, the cross validation will exit with an error if the extra regressor is constant in the simulated history. The `initial` period should be long enough for the extra regressor to take on multiple values. Similarly, the initial period should be long enough to capture any seasonalities that are included in the model: at least a year for yearly seasonality, at least a week for weekly seasonality, etc."
+    "The `initial` period should be long enough to capture all of the components of the model, in particular seasonalities and extra regressors: at least a year for yearly seasonality, at least a week for weekly seasonality, etc."
    ]
   }
  ],
@@ -496,7 +496,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
-   "version": "2.7.14+"
+   "version": "2.7.13"
   }
  },
  "nbformat": 4,

notebooks/seasonality,_holiday_effects,_and_regressors.ipynb

@@ -888,7 +888,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "NFL Sundays could also have been handled using the \"holidays\" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known. The regressor cannot be constant in the training data; fitting will exit with an error if it is.\n",
+    "NFL Sundays could also have been handled using the \"holidays\" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known.\n",
     "\n",
     "The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R. Note that regressors must be added prior to model fitting.\n",
     "\n",