From 58c76b9d2d8933485e185d275a0c1a3cea85f9c8 Mon Sep 17 00:00:00 2001
From: Nicholas Walsh <nicholaswalsh.official@gmail.com>
Date: Thu, 24 May 2018 18:35:53 -0700
Subject: [PATCH] add R notebook (system level commands need to be tested)

---
 examples/R/.datmo/.config               |  22 ++++++
 examples/R/.datmo/database/config.json  |   1 +
 examples/R/snapshot-create-notebook.Rmd | 101 ++++++++++++++++++++++++
 3 files changed, 124 insertions(+)
 create mode 100644 examples/R/.datmo/.config
 create mode 100644 examples/R/.datmo/database/config.json
 create mode 100644 examples/R/snapshot-create-notebook.Rmd

diff --git a/examples/R/.datmo/.config b/examples/R/.datmo/.config
new file mode 100644
index 00000000..7de53863
--- /dev/null
+++ b/examples/R/.datmo/.config
@@ -0,0 +1,22 @@
+{
+    "controller.code.driver": {
+        "class_constructor": "datmo.core.controller.code.driver.git.GitCodeDriver",
+        "options": {
+            "execpath": "git",
+            "filepath": "/Users/nwalsh/Dev/datmo/examples/R"
+        }
+    },
+    "storage.driver": {
+        "class_constructor": "datmo.core.storage.driver.blitzdb_dal_driver.BlitzDBDALDriver",
+        "options": {
+            "connection_string": "/Users/nwalsh/Dev/datmo/examples/R/.datmo/database",
+            "driver_type": "file"
+        }
+    },
+    "storage.local": {
+        "class_constructor": "datmo.core.storage.local.dal.LocalDAL",
+        "options": {
+            "driver": "storage.driver"
+        }
+    }
+}
\ No newline at end of file
diff --git a/examples/R/.datmo/database/config.json b/examples/R/.datmo/database/config.json
new file mode 100644
index 00000000..ed6bf090
--- /dev/null
+++ b/examples/R/.datmo/database/config.json
@@ -0,0 +1 @@
+{"autocommit": false, "serializer_class": "json", "store_class": "transactional", "index_class": "transactional", "indexes": {"code": {"pk": {"id": "ffa1801b0c3e45e081be8f4ce3bcf101", "key": "pk"}}, "file_collection": {"pk": {"id": "6b27ceaecadf4f2eaf9b31ccddbcb09c", "key": "pk"}}, "task": {"pk": {"id": "84110dc049e8452596451b76c05833f4", "key": "pk"}}, "environment": {"pk": {"id": "9d26bd0b5f08454d9497864962b97fc2", "key": "pk"}}, "session": {"pk": {"id": "8f0ca64ddfc14abd89901e987cfdeeb0", "key": "pk"}}, "snapshot": {"pk": {"id": "0df27a73b2974aad9c0b163362adb923", "key": "pk"}}, "user": {"pk": {"id": "be646c50d4564f5cbf58fd1af17807d7", "key": "pk"}}, "model": {"pk": {"id": "45cd516f77f94921876cd86c4528b8d0", "key": "pk"}}}, "index_store_class": "basic", "version": "0.2.12"}
\ No newline at end of file
diff --git a/examples/R/snapshot-create-notebook.Rmd b/examples/R/snapshot-create-notebook.Rmd
new file mode 100644
index 00000000..08e5b2e0
--- /dev/null
+++ b/examples/R/snapshot-create-notebook.Rmd
@@ -0,0 +1,101 @@
+---
+title: "Log your experiments in R with Datmo"
+author: "Nick Walsh"
+output:
+  html_document:
+    df_print: paged
+    toc: yes
+  rmarkdown::html_vignette:
+    number_sections: yes
+    toc: yes
+---
+
+Setup
+=====
+
+First, we'll need to install a few packages for use today. They'll contain everything we'll need to model our data and create visualizations.
+
+```{r installPackages}
+install.packages("datasets") # Package that contains the Iris dataset
+install.packages("caret", dependencies = TRUE) # Model selection/tuning package
+install.packages("rpart.plot") # Visualization package
+```
+
+We're going to install a python package called Datmo, which will enable us to log and track our experiments through the power of *snapshots*.
+If you don't already have pip, you can [find it here](https://pip.pypa.io/en/stable/installing/).
+
+```{bash}
+pip install datmo
+```
+
+Next, we're going to want to make sure we've set the proper working directory. We can do this easily through the 
+RStudio file finder on the right, or with the following command.
+
+This will be necessary so that Datmo knows the proper directory to perform tracking in. 
+
+```{r "setup", include=FALSE}
+require("knitr")
+opts_knit$set(root.dir = "~/Dev/datmo-R-example") # Replace with whatever your root directory for the project is
+```
+
+Now we're going to initialize a Datmo repository. This will enable us to create snapshots for logging our experiments.
+
+```{r initializeDatmo}
+system("datmo init", input=c("my new project","test description"), timeout=15)
+```
+
+Example
+======
+
+Ok, time to start with loading in the Fisher Iris dataset.
+
+```{r loadData}
+library(datasets)
+
+df <- iris # Create dataframe from the Iris dataset
+head(df) # View first few rows of dataset
+```
+
+Now that our dataframe is loaded in, we can import the *caret* package to perform training.
+
+```{r fitModel}
+library(caret)
+
+modFit <- train(Species ~., method = "rpart", data=df) #Fit model
+print(modFit$finalModel)   #Summarize model
+```
+
+Our model is built, but it's kind of hard to comprehend with just the metrics. Let's create a visualization to showcase the
+splits in our decision tree.
+
+```{r visualizeModel}
+library(rpart.plot)
+
+rpart.plot(modFit$finalModel) #create decision tree visualization
+```
+
+Awesome! Since we're happy with our model results, we'll want to save our model and log configuration and stats sections in a snapshot.
+We can do this with the following syntax, where we're creating a *char* string of format "--PROPERTY key:value" that will be passed to 
+the snapshot create code block.
+
+```{r defineSnapshot}
+config<- paste(sep="",
+               " --config method:", modFit$method,
+               " --config modelType:", modFit$modelType)
+
+#define metrics to save from the model
+stats<- paste(sep="",
+              " --stats Accuracy:", modFit$results$Accuracy[1],
+              " --stats Kappa:", modFit$results$Kappa[1])
+
+config
+stats
+```
+
+```{bash snapshotCreate}
+system2("datmo", args=paste("snapshot create", "-m 'Whoah, my first snapshot!'", config, stats), timeout=30)
+```
+
+```{bash}
+datmo snapshot ls
+```