From 622477f19f448a78230425936bdcdcde37af850e Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Thu, 12 Aug 2021 17:38:08 +0200
Subject: [PATCH] [WIP] Start merging steps into a class for a pipeline.

---
 exploration/ex_ml_pipeline.py | 14 ++++++++++++++
 machine_learning/pipeline.py  | 12 ++++++++++++
 2 files changed, 26 insertions(+)
 create mode 100644 machine_learning/pipeline.py

diff --git a/exploration/ex_ml_pipeline.py b/exploration/ex_ml_pipeline.py
index 4e7e542..8d1fcdb 100644
--- a/exploration/ex_ml_pipeline.py
+++ b/exploration/ex_ml_pipeline.py
@@ -148,3 +148,17 @@ lin_reg_proximity.score(
     df_full_data_daily_means[["freq_prox_near", "prop_prox_near"]],
     df_full_data_daily_means["PA"],
 )
+
+# %% [markdown]
+# # Merging these into a pipeline
+
+# %%
+from machine_learning import pipeline
+
+# %%
+ml_pipeline = pipeline.MachineLearningPipeline()
+
+# %%
+ml_pipeline.participants_usernames
+
+# %%
diff --git a/machine_learning/pipeline.py b/machine_learning/pipeline.py
new file mode 100644
index 0000000..a07a468
--- /dev/null
+++ b/machine_learning/pipeline.py
@@ -0,0 +1,12 @@
+import datetime
+
+import participants.query_db
+
+
+class MachineLearningPipeline:
+    def __init__(self, participants_usernames=None):
+        if participants_usernames is None:
+            participants_usernames = participants.query_db.get_usernames(
+                collection_start=datetime.date.fromisoformat("2020-08-01")
+            )
+        self.participants_usernames = participants_usernames