From 53c6459f2be8b7526616ba35a709f855995ddddf Mon Sep 17 00:00:00 2001
From: Carlos Hernandez <cxh@stanford.edu>
Date: Sun, 19 Jun 2016 11:37:24 -0700
Subject: [PATCH] start getting started

---
 .gitignore               |  3 ++
 docs/getting_started.rst | 70 +++++++++++++++++++++++++++++++++++++++-
 2 files changed, 72 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index d26dbea..4ab0da3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -56,3 +56,6 @@ MANIFEST
 
 # vim
 *.swp
+
+#Notebooks
+.ipynb_checkpoints
diff --git a/docs/getting_started.rst b/docs/getting_started.rst
index c3ce665..7505e29 100644
--- a/docs/getting_started.rst
+++ b/docs/getting_started.rst
@@ -1,2 +1,70 @@
+
 Getting Started
-===============
\ No newline at end of file
+===============
+
+Getting started with Osprey is as easy as setting up a single ``YAML``
+configuration file. This configuration file will contain your model
+estimators (``estimator``), hyperparameter search strategy
+(``strategy``), hyperparameter search space (``search_space``), dataset
+information (``dataset_loader``), cross-validation strategy (``cv``),
+and a path to a ``SQL``-like database (``trials``). This page will go
+over how to set up a basic Osprey toy project and then a more realistic
+example for a `molecular
+dynamics <https://en.wikipedia.org/wiki/Molecular_dynamics>`__ dataset.
+
+First, we'll begin with a simple C-Support Vector Classification example
+using ``sklearn`` to introduce the basic ``YAML`` fields for Osprey. To
+tell Osprey that we want to use ``sklearn``'s ``SVC`` as our estimator,
+we can type:
+
+.. code:: yaml
+
+    estimator:
+      entry_point: sklearn.svm.SVC
+
+If we want to use `gaussian process
+prediction <https://en.wikipedia.org/wiki/Gaussian_process#Gaussian_process_prediction.2C_or_kriging>`__
+to decide where to search in hyperparameter space, we can add:
+
+.. code:: yaml
+
+    strategy:
+      name: gp
+      params:
+        seeds: 5
+
+The search space can be defined for any hyperparameter available in the
+``estimator`` class. Here we can adjust the value range of the ``C`` and
+``gamma`` hyperparamters. We'll search over a range of 0.1 to 10 for
+``C`` and over 1E-5 to 1 in log-space (note: ``warp: log``) for
+``gamma``.
+
+.. code:: yaml
+
+    search_space:
+      C:
+        min: 0.1
+        max: 10
+        type: float
+
+      gamma:
+        min: 1e-5
+        max: 1
+        warp: log
+        type: float
+
+.. code:: yaml
+
+    cv: 5
+
+.. code:: yaml
+
+    dataset_loader:
+      name: sklearn_dataset
+      params:
+        method: load_digits
+
+.. code:: yaml
+
+    trials:
+        uri: sqlite:///osprey-trials.db