#1 Prepare data

.gitignore

@@ -127,3 +127,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# PyCharm
+.idea/

README.md

@@ -1,2 +1,26 @@
 # ml-storybooks-recommender
+
 Machine learning model which predicts the rating of unread storybooks based on the student's previously read storybooks.
+
+One model will be trained per language.
+
+
+## 1. Prepare the Data
+
+To prepare the data, follow these steps:
+  * Open `prepare_data.py` and select environment and language.
+  * Go to the website corresponding to the chosen environment and language, e.g. http://eng.test.elimu.ai.
+  * Download `storybooks.csv` from http://eng.test.elimu.ai/content/storybook/list.
+  * Download `storybook-learning-events.csv` from http://eng.test.elimu.ai/analytics/storybook-learning-event/list.
+  * Add the two datasets to `RAW_DATA_DIR`.
+  * Execute the script: `python prepare_data.py`
+
+
+## 2. Train the Model
+
+TODO
+
+
+## 3. Make Predictions on New Samples
+
+TODO

env-TEST/lang-ENG/data/storybook-learning-events.csv

@@ -0,0 +1,26 @@
+id,time,android_id,package_name,storybook_id,learning_event_type
+45,1603495877976,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+44,1603495780823,7394f9d23bfd74af,ai.elimu.vitabu.test,24,STORYBOOK_OPENED
+43,1603495757361,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+42,1603494702681,7394f9d23bfd74af,ai.elimu.vitabu.test,23,STORYBOOK_OPENED
+41,1603494681753,7394f9d23bfd74af,ai.elimu.vitabu.test,24,STORYBOOK_OPENED
+40,1603494581648,7394f9d23bfd74af,ai.elimu.vitabu.test,24,STORYBOOK_OPENED
+39,1603494430877,7394f9d23bfd74af,ai.elimu.vitabu.test,27,STORYBOOK_OPENED
+38,1603494363802,7394f9d23bfd74af,ai.elimu.vitabu.test,27,STORYBOOK_OPENED
+37,1603494110370,7394f9d23bfd74af,ai.elimu.vitabu.test,26,STORYBOOK_OPENED
+36,1603493867772,7394f9d23bfd74af,ai.elimu.vitabu.test,25,STORYBOOK_OPENED
+35,1603493388681,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+34,1603493323420,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+33,1603493261035,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+32,1603493235566,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+31,1603493014112,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+30,1603492973830,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+29,1603492930084,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+28,1603492919979,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+27,1603492918728,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+26,1603492908493,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+25,1603492907090,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+24,1603492903577,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+23,1603492807897,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+22,1603492757816,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED
+21,1603492731620,7394f9d23bfd74af,ai.elimu.vitabu.test,22,STORYBOOK_OPENED