Adds documentation showing scalar creation & input

README.md

@@ -68,6 +68,8 @@ def spend_per_signup(spend: pd.Series, signups: pd.Series) -> pd.Series:
 The astute observer will notice we have not defined `spend` or `signups` as functions. That is okay,
 this just means these need to be provided as input when we come to actually wanting to create a dataframe.
 
+Note: functions can take or create scalar values too.
+
 2. Create a `my_script.py` which is where code will live to tell Hamilton what to do:
 ```python
 import importlib
@@ -80,6 +82,7 @@ from hamilton import driver
 logger = logging.getLogger(__name__)
 logging.basicConfig(stream=sys.stdout)
 initial_columns = {  # load from actuals or wherever -- this is our initial data we use as input.
+    # Note: these do not have to be all series, they could be scalar inputs.
     'signups': pd.Series([1, 10, 50, 100, 200, 400]),
     'spend': pd.Series([10, 10, 20, 40, 40, 50]),
 }

examples/hello_world/my_functions.py

@@ -9,3 +9,23 @@ def avg_3wk_spend(spend: pd.Series) -> pd.Series:
 def spend_per_signup(spend: pd.Series, signups: pd.Series) -> pd.Series:
     """The cost per signup in relation to spend."""
     return spend / signups
+
+
+def spend_mean(spend: pd.Series) -> float:
+    """Shows function creating a scalar. In this case it computes the mean of the entire column."""
+    return spend.mean()
+
+
+def spend_zero_mean(spend: pd.Series, spend_mean: float) -> pd.Series:
+    """Shows function that takes a scalar. In this case to zero mean spend."""
+    return spend - spend_mean
+
+
+def spend_std_dev(spend: pd.Series) -> float:
+    """Function that computes the standard deviation of the spend column."""
+    return spend.std()
+
+
+def spend_zero_mean_unit_variance(spend_zero_mean: pd.Series, spend_std_dev: float) -> pd.Series:
+    """Function showing one way to make spend have zero mean and unit variance."""
+    return spend_zero_mean / spend_std_dev

examples/hello_world/my_script.py

@@ -8,6 +8,7 @@
 logger = logging.getLogger(__name__)
 logging.basicConfig(stream=sys.stdout)
 initial_columns = {  # load from actuals or wherever -- this is our initial data we use as input.
+    # Note: these values don't have to be all series, they could be a scalar.
     'signups': pd.Series([1, 10, 50, 100, 200, 400]),
     'spend': pd.Series([10, 10, 20, 40, 40, 50]),
 }
@@ -21,6 +22,7 @@
     'signups',
     'avg_3wk_spend',
     'spend_per_signup',
+    'spend_zero_mean_unit_variance'
 ]
 # let's create the dataframe!
 df = dr.execute(output_columns, display_graph=True)