kxzk

{#
dev_limit

A macro to limit the number of rows
processed during development and staging.
In production, the limit is removed.

By default, the macro runs using
the bernoulli sampling method.
However, the system method is faster,

kxzk

{#
<insert_macro_name>

<insert_description>

usage:
    {{ insert_macro_name(some_value) }}
    (sql) -> <insert sql generated>
    {{ insert_macro_name(some_value, some_value) }}
    (sql) -> <insert sql generated>

kxzk

${project-name} Change Log

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog and this project adheres to Semantic Versioning.

1.0.0

• engage

kxzk

# Specify columns, so DataFrame isn't overwritten
df[["first_name", "last_name", "email"]] = df.select_dtypes(
  include=["object"]).apply(lambda x: x.str.lower()
)

kxzk

from pandas.api.types import infer_dtype

infer_dtype(["john", np.nan, "jack"], skipna=True)
# string

infer_dtype(["john", np.nan, "jack"], skipna=False)
# mixed

kxzk

from pandas.api.types import is_numeric_dtype

is_numeric_dtype("hello world")
# False

kxzk

from pandas.util.testing import assert_frame_equal

# Methods for Series and Index as well
assert_frame_equal(df_1, df_2)

kxzk

from pandas.api.types import union_categoricals

food = pd.Categorical(["burger king", "wendys"])
food_2 = pd.Categorical(["burger king", "chipotle"])

union_categoricals([food, food_2])

kxzk

df["age_sqrt"] = np.sqrt(df["age"])

kxzk

df["age_reciprocal"] = 1.0 / df["age"]