| import contextlib | |
| from functools import partial | |
| from sklearn.pipeline import Pipeline | |
| @contextlib.contextmanager | |
| def intermediate_transforms(pipe: Pipeline, keys: list=[], bypass_list: list=[]): | |
| """Allows for the retrieval of all or parts of the transformations in a | |
| sklearn Pipeline, as well as the ability to dynamically bypass parts of | |
| the pipeline. |
This borrows from https://jordanthomasg.medium.com/python-development-on-macos-with-pyenv-2509c694a808.
Install Homebrew if necessary.
/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
Before installing pyenv do the following:
| import logging | |
| from collections.abc import Iterable | |
| def is_container(obj): | |
| return isinstance(obj, Iterable) and not isinstance(obj, (str, bytes, bytearray)) | |
| # https://stackoverflow.com/a/54000999/394430 | |
| def walk_collection(obj, callback=None, _path: list=[], **kwargs): | |
| """Walk an arbitrarily nested structure of lists and/or dicts such as would be made when | |
| reading JSON as an object. Walking is performed in a depth-first search manner. |
To get use MongoDB from Tableau, start a mongosqld instance...
mongosqld --mongo-uri "mongodb://<host>:<port>/?connect=direct"
Then from Tableau, select Servers->MongoDB BI Connector with 127.0.0.1 and 3307 as connection details.
This creates a normalized mass density histogram in matplotlib
bins = np.linspace(-1, 1, 101)
# To get a normalized mass density histogram, we have to do it this way...
hist, bins = np.histogram(df['some_column'], bins=bins, density=True)
hist /= len(bins)
width = bins[1]-bins[0]
fig = plt.figure(figsize=(8, 4))
ax = fig.add_axes([.15, .15, .75, .75])
plt.bar(left=bins[:-1], height=hist, width=width)