Adds code for pregnancy due date modeling blog post

examples/due_date_probabilities/README.md

@@ -0,0 +1,22 @@
+# Modeling Pregnancy Due Dates using Hamilton
+
+This is an example of developing and applying a simple statistical model using Hamilton
+for a very common problem. What is the probability that a baby will be born (before, on, after)
+X date?
+
+
+You can find the notebook on google collab here:
+<a target="_blank" href="https://colab.research.google.com/github/DAGWorks-Inc/hamilton/blob/main/examples/due_date_probabilities/notebook.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open Me In Google Colab"/>
+</a>
+
+You can read the full description in the [post](https://blog.dagworks.io/p/181bb751-2e58-4e76-8d53-5a8c81ea16cb).
+
+In this, you'll find the following files:
+
+1. [notebook.ipynb](notebook.ipynb) - The Jupyter notebook that walks through the process of developing/running the model.
+2. [base_dates.py] -- a Hamilton module that generates date-related series
+3. [probability_estimation.py] -- a Hamilton module that computes a statistical model (estimating parameters for probability due dates)
+4. [probabilities.py] -- a Hamilton module that runs that model over a set of dates
+
+Run the notebook to see the process of developing the model and running it.

examples/due_date_probabilities/base_dates.py

@@ -0,0 +1,21 @@
+import datetime
+
+import pandas as pd
+
+
+def due_date(start_date: datetime.datetime) -> datetime.datetime:
+    """The due date is start_date + 40 weeks. Start date is the date of the expecting mother's last period"""
+    return start_date + datetime.timedelta(weeks=40)
+
+
+def possible_dates(
+    due_date: datetime.datetime,
+    buffer_before_due_date: int = 8 * 7,
+    buffer_after_due_date: int = 4 * 7,
+) -> pd.Series:
+    """Gets all the reasonably possible dates (-8 weeks, + 4 weeks) of delivery"""
+    idx = pd.date_range(
+        due_date - datetime.timedelta(days=buffer_before_due_date),
+        due_date + datetime.timedelta(days=buffer_after_due_date),
+    )
+    return pd.Series(data=idx, index=idx)