amrakm

## source: http://nbviewer.jupyter.org/github/rasbt/algorithms_in_ipython_notebooks/blob/master/ipython_nbs/statistics/linregr_least_squares_fit.ipynb#Sections

import numpy as np

np.testing.assert_almost_equal(arr_1, arr_2, decimal=5) 
  
    
    

amrakm

# source: http://nbviewer.jupyter.org/github/rasbt/algorithms_in_ipython_notebooks/blob/master/ipython_nbs/statistics/linregr_least_squares_fit.ipynb#Sections
# source_2: https://github.com/rasbt/data-science-tutorial/blob/master/code/linear-reqression-leastsquares.ipynb

import numpy as np

def matrix_lstsqr(x, y):
    """ Computes the least-squares solution to a linear matrix equation. """
    X = np.vstack([x, np.ones(len(x))]).T
    return (np.linalg.inv(X.T.dot(X)).dot(X.T)).dot(y)
    

amrakm

def normalised_hist(x):
    counts, ranges = np.histogram(x.dropna(), range=(min(x), max(x)))
    weights = np.ones_like(x.shape[0])/float(x.shape[0])
    normalised_counts = counts * weights
    ranges = ranges.astype(int)
    return pd.Series(normalised_counts, zip(ranges[:-1], ranges[1:]))

kw = dict(stacked=True, width=1, rot=45)

df.groupby('flag').get_group(True)[['numerical_att')]].apply(normalised_hist).unstack(0).plot.bar(**kw)

amrakm

## source: https://www.kaggle.com/jeru666/did-you-think-of-these-features

def change_datatype(df):
    int_cols = list(df.select_dtypes(include=['int']).columns)
    for col in int_cols:
        if ((np.max(df[col]) <= 127) and(np.min(df[col] >= -128))):
            df[col] = df[col].astype(np.int8)
        elif ((np.max(df[col]) <= 32767) and(np.min(df[col] >= -32768))):
            df[col] = df[col].astype(np.int16)
        elif ((np.max(df[col]) <= 2147483647) and(np.min(df[col] >= -2147483648))):

amrakm

ranges = [0,50,100,160]
ranges_label = ['cheap', "average", "expensive"]
df['price_cat'] = pd.cut(df.current_package_price, ranges, labels=ranges_label)

# Another example
# Bucketing age groups

ranges = [18,25,29,34, 50,70, 2020]
ranges_label = ['18-25','26-29',"30-34", "35-50", '51-70','unknown']
df['age_group'] = pd.cut(df['age'], ranges, labels=ranges_label)

amrakm

## pip install gender-guesser

import gender_guesser.detector as gender

def get_gender(x):
    d = gender.Detector()
    return d.get_gender(x.lower().capitalize())

amrakm

# source: https://stackoverflow.com/a/52672859/5554394

from IPython.display import clear_output
from matplotlib import pyplot as plt
import collections
%matplotlib inline

def live_plot(data_dict, figsize=(7,5), title=''):
    clear_output(wait=True)
    plt.figure(figsize=figsize)

amrakm

#!/usr/bin/env python

"""
Convert camel-case to snake-case in python.

e.g.: CamelCase -> snake_case

Relevant StackOverflow question: http://stackoverflow.com/a/1176023/293064
"""

amrakm

import warnings
warnings.filterwarnings('ignore')
warnings.simplefilter('ignore')

amrakm

import matplotlib as mpl
import matplotlib.pyplot as plt

large = 22; med = 16; small = 12
params = {'axes.titlesize': large,
          'legend.fontsize': med,
          'figure.figsize': (16, 10),
          'axes.labelsize': med,
          'axes.titlesize': med,
          'xtick.labelsize': med,