Merge branch 'main' into python_3_11

.all-contributorsrc

@@ -121,7 +121,8 @@
       "avatar_url": "https://avatars.githubusercontent.com/u/16029092?v=4",
       "profile": "https://github.com/shagn",
       "contributions": [
-        "bug"
+        "bug",
+        "doc"
       ]
     },
     {
@@ -258,6 +259,33 @@
       "contributions": [
         "code"
       ]
+    },
+    {
+      "login": "yibenhuang",
+      "name": "Yiben Huang",
+      "avatar_url": "https://avatars.githubusercontent.com/u/62163340?v=4",
+      "profile": "https://github.com/yibenhuang",
+      "contributions": [
+        "doc"
+      ]
+    },
+    {
+      "login": "andrewgross",
+      "name": "Andrew Gross",
+      "avatar_url": "https://avatars.githubusercontent.com/u/370118?v=4",
+      "profile": "https://github.com/andrewgross",
+      "contributions": [
+        "doc"
+      ]
+    },
+    {
+      "login": "taniishkaaa",
+      "name": "taniishkaaa",
+      "avatar_url": "https://avatars.githubusercontent.com/u/109246904?v=4",
+      "profile": "https://github.com/taniishkaaa",
+      "contributions": [
+        "doc"
+      ]
     }
   ],
   "contributorsPerLine": 7,

.github/release-drafter.yml

@@ -14,6 +14,7 @@ categories:
   - title: 'Enhancement'
     label: 'enhancement'
 change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
+commitish: main
 template: |
   ## Changes
   $CHANGES

.gitignore

@@ -7,6 +7,7 @@ docs/_site
 build
 dist
 .vscode
+.idea
 *.gif
 *.csv
 */data/*

action_files/test_dask.py

@@ -1,12 +1,24 @@
 import dask.dataframe as dd
+import pytest
 
 from statsforecast.utils import generate_series
-from .utils import pipeline
+from .utils import pipeline, pipeline_with_level
 
-def test_dask_flow():
-    n_series = 2
-    horizon = 7
+@pytest.fixture()
+def n_series():
+    return 2
+
+@pytest.fixture()
+def sample_data(n_series):
     series = generate_series(n_series).reset_index()
     series['unique_id'] = series['unique_id'].astype(str)
     series = dd.from_pandas(series, npartitions=2)
-    pipeline(series, n_series, horizon)
+    return series
+
+def test_dask_flow(sample_data, n_series):
+    horizon = 7
+    pipeline(sample_data, n_series, horizon)
+
+def test_dask_flow_with_level(sample_data, n_series):
+    horizon = 7
+    pipeline_with_level(sample_data, n_series, horizon)

action_files/test_ray.py

@@ -1,14 +1,24 @@
+import pytest
 import ray
 
 from statsforecast.utils import generate_series
-from .utils import pipeline
+from .utils import pipeline, pipeline_with_level
 
-def test_ray_flow():
-    n_series = 2
-    horizon = 7
+@pytest.fixture()
+def n_series():
+    return 2
+
+@pytest.fixture()
+def sample_data(n_series):
     series = generate_series(n_series).reset_index()
     series['unique_id'] = series['unique_id'].astype(str)
-    ctx = ray.data.context.DatasetContext.get_current()
-    ctx.use_streaming_executor = False
     series = ray.data.from_pandas(series).repartition(2)
-    pipeline(series, n_series, horizon)
+    return series
+
+def test_ray_flow(sample_data, n_series):
+    horizon = 7
+    pipeline(sample_data, n_series, horizon)
+
+def test_ray_flow_with_level(sample_data, n_series):
+    horizon = 7
+    pipeline_with_level(sample_data, n_series, horizon)

action_files/test_spark.py

@@ -1,13 +1,26 @@
+import pytest
 from pyspark.sql import SparkSession
 
 from statsforecast.utils import generate_series
-from .utils import pipeline
+from .utils import pipeline, pipeline_with_level
 
-def test_spark_flow():
+@pytest.fixture()
+def n_series():
+    return 2
+
+@pytest.fixture()
+def sample_data(n_series):
     n_series = 2
-    horizon = 7
     series = generate_series(n_series).reset_index()
     series['unique_id'] = series['unique_id'].astype(str)
     spark = SparkSession.builder.getOrCreate()
     series = spark.createDataFrame(series).repartition(2, 'unique_id')
-    pipeline(series, n_series, horizon)
+    return series
+
+def test_spark_flow(sample_data, n_series):
+    horizon = 7
+    pipeline(sample_data, n_series, horizon)
+
+def test_spark_flow_with_level(sample_data, n_series):
+    horizon = 7
+    pipeline_with_level(sample_data, n_series, horizon)

action_files/utils.py

@@ -41,7 +41,19 @@ def pipeline(series, n_series, horizon):
         models=models,
         freq='D',
     )
-    forecast = fa.as_pandas(sf.forecast(df=series, h=horizon, level=[80, 90]))
+    forecast = fa.as_pandas(sf.forecast(df=series, h=horizon))
     print(forecast)
     assert forecast.shape == (n_series * horizon, len(models) + 2)
 
+def pipeline_with_level(series, n_series, horizon):
+    models = [
+		AutoARIMA(season_length=7), 
+	]
+    sf = StatsForecast(
+        models=models,
+        freq='D',
+    )
+    forecast = fa.as_pandas(sf.forecast(df=series, h=horizon, level=[80, 90]))
+    print(forecast.columns)
+    expected = ["unique_id","ds","AutoARIMA","AutoARIMA-lo-90","AutoARIMA-hi-90", "AutoARIMA-lo-80","AutoARIMA-hi-80"]
+    assert forecast.shape == (n_series * horizon, len(expected))

nbs/.gitignore

@@ -1 +1,3 @@
 /.quarto/
+
+lightning_logs/

nbs/_quarto.yml

@@ -24,7 +24,7 @@ website:
     collapse-below: lg
     left:
       - text: "Get Started"
-        href: docs/getting-started/Getting_Started_short.ipynb
+        href: docs/getting-started/getting_started_short.html
       - text: "NixtlaVerse"
         menu:
           - text: "StatsForecast ⚡️"

nbs/docs/getting-started/Installation.ipynb → nbs/docs/getting-started/0_Installation.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "14f5686c-449b-4376-8c58-fc8141f4b0f8",
    "metadata": {},
@@ -11,6 +12,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "0f1d1483-6da7-4372-8390-84c9c280109e",
    "metadata": {},

nbs/docs/getting-started/Getting_Started_short.ipynb → nbs/docs/getting-started/1_Getting_Started_short.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -10,13 +11,14 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "`StatsForecast` follows the sklearn model API. For this minimal example, you will create an instance of the StatsForecast class and then call its `fit` and `predict` methods. We recommend this option if speed is not paramount and you want to explore the fitted values and parameters. \n",
     "\n",
     ":::{.callout-tip}\n",
-    "If you want to forecast many series, we recommend using the `forecast` method. Check this [Getting Started with multiple time series](./Getting_Started_multiple.ipynb) guide. \n",
+    "If you want to forecast many series, we recommend using the `forecast` method. Check this [Getting Started with multiple time series](./2_Getting_Started_complete.ipynb) guide. \n",
     ":::\n",
     "\n",
     "The input to StatsForecast is always a data frame in [long format](https://www.theanalysisfactor.com/wide-and-long-data/) with three columns: `unique_id`, `ds` and `y`:\n",
@@ -30,7 +32,7 @@
     "\n",
     "As an example, let’s look at the US Air Passengers dataset. This time series consists of monthly totals of a US airline passengers from 1949 to 1960. The CSV is available [here](https://www.kaggle.com/datasets/chirag19/air-passengers).\n",
     "\n",
-    "We assume you have StatsForecast already installed. Check this guide for instructions on [how to install StatsForecast](./Installation.ipynb).\n",
+    "We assume you have StatsForecast already installed. Check this guide for instructions on [how to install StatsForecast](./0_Installation.ipynb).\n",
     "\n",
     "First, we’ll  import the data:"
    ]
@@ -39,18 +41,10 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "UsageError: unrecognized arguments: hide output\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "%%capture #To hide output \n",
-    "! pip install StatsForecast"
+    "#| hide\n",
+    "! pip install statsforecast"
    ]
   },
   {
@@ -148,14 +142,15 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "We fit the model by instantiating a new `StatsForecast` object with its two required parameters:\n",
+    "https://nixtla.github.io/statsforecast/src/core/models.html\n",
+    "* `models`: a list of models. Select the models you want from [models](../../src/core/models.ipynb) and import them. For this example, we will use a `AutoARIMA` model. We set `season_length` to 12 because we expect seasonal effects every 12 months. (See: [Seasonal periods](https://robjhyndman.com/hyndsight/seasonal-periods/))\n",
     "\n",
-    "* `models`: a list of models. Select the models you want from [models](../models.ipynb) and import them. For this example, we will use a `AutoARIMA` model. We set `season_length` to 12 because we expect seasonal effects every 12 months. (See: [Seasonal periods](https://robjhyndman.com/hyndsight/seasonal-periods/))\n",
-    "\n",
-    "* `freq`: a string indicating the frequency of the data. (See [panda's available frequencies](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases).)\n",
+    "* `freq`: a string indicating the frequency of the data. (See [pandas available frequencies](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases).)\n",
     "\n",
     "Any settings are passed into the constructor. Then you call its fit method and pass in the historical data frame.\n",
     "\n",
@@ -184,6 +179,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -297,6 +293,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -1741,15 +1738,16 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     ":::{.callout-tip}\n",
     "## Next Steps\n",
     "\n",
-    "* Build and end to end forecasting pipeline following best practices in [End to End Walkthrough](./Getting_Started_complete.ipynb)\n",
-    "* [Forecast millions of series](./ForecastingAtScale.ipynb) in a scalable cluster in the cloud using Spark and Nixtla\n",
-    "* [Detect anomalies](./AnomalyDetection.ipynb) in your past observations\n",
+    "* Build and end-to-end forecasting pipeline following best practices in [End to End Walkthrough](./2_Getting_Started_complete.ipynb)\n",
+    "* [Forecast millions of series](../how-to-guides/Prophet_spark_m5.ipynb) in a scalable cluster in the cloud using Spark and Nixtla\n",
+    "* [Detect anomalies](../tutorials/AnomalyDetection.ipynb) in your past observations\n",
     ":::"
    ]
   }