shaypal5

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

def print_confusion_matrix(confusion_matrix, class_names, figsize = (10,7), fontsize=14):
    """Prints a confusion matrix, as returned by sklearn.metrics.confusion_matrix, as a heatmap.
    
    Note that due to returning the created figure object, when this funciton is called in a
    notebook the figure willl be printed twice. To prevent this, either append ; to your
    function call, or modify the function by commenting out the return expression.

shaypal5

# 1. install dependencies
sudo apt install libncurses5-dev libgnome2-dev libgnomeui-dev \
    libgtk2.0-dev libatk1.0-dev libbonoboui2-dev \
    libcairo2-dev libx11-dev libxpm-dev libxt-dev python-dev \
    python3-dev ruby-dev lua5.1 lua5.1-dev libperl-dev git
    
# 2. remove vim 
sudo apt remove vim vim-runtime gvim
sudo apt remove vim-tiny vim-common vim-gui-common vim-nox

shaypal5

language: python
# ===== Linux ======
os: linux
dist: xenial
python:
  - 2.7
  - 3.6
  - 3.7
  - 3.8
  - 3.9

shaypal5

image: python:3.8.3

# pipeline stages definitions
test: &test
  step:
    name: test
    caches:
      - pip
    script:
      - python --version

shaypal5

Taken from a post by Stuart Colville at https://muffinresearch.co.uk/selectively-including-parts-readme-rst-in-your-docs/. Here only to make this star-able by myself.

In your README.rst add a marker marking from which point you want to start importing content:

Blah blah project  
=================

Here's all the actual readme content.

shaypal5

from typing import Optional
import pdpipe as pdp
from pdpipe import df
from sklearn.linear_model import LogisticRegression
from pdpipe.skintegrate import PdPipelineAndSklearnEstimator

class MyPipelineAndModel(PdPipelineAndSklearnEstimator):
    
    def __init__(
        self,

shaypal5

>>> mp = MyPipelineAndModel(
      savings_max_val=101,
      drop_gender=False,
      standardize=True,
      ohencode_country=True,
      savings_bin_val=1,
      pca_threshold=25,
      fit_intercept=True)
>>> mp
<PdPipeline -> LogisticRegression>

shaypal5

>>> df = pd.DataFrame(
...   [[23, 'Jo', 45], [19, 'Bo', 72], [15, 'Di', 12], [5, 'Jo', 0]],
...   columns=['age', 'name', 'salary'])
>>> df
   age name  salary
0   23   Jo      45
1   19   Bo      72
2   15   Di      12
3    5   Jo       0
>>> pipeline = pdp.DropDuplicates('name').Bin({'salary': [0, 20, 50]}) \

shaypal5

from typing import Tuple, Optional
import numpy as np
import pandas as pd


def train_val_split(
    training_df: pd.DataFrame,
    val_ratio: float,
) -> Tuple[pd.DataFrame, pd.DataFrame]:
    """Splits the input training dataset into train/val set.

shaypal5

>>> df = pd.DataFrame(
        data=[[4, 165, 'USA'], [2, 180, 'UK'], [2, 170, 'Greece']],
        index=['Dana', 'Jane', 'Nick'],
        columns=['Medals', 'Height', 'Born']
    )
>>> df
      Medals  Height    Born
Dana       4     165     USA
Jane       2     180      UK
Nick       2     170  Greece