Midterm Cheat Sheet

Midterm Cheat Sheet October 9, 2023 1 Midterm Cheat Sheet 1.1 Initialization Code Block [32]: ## Do not change this cell, only execute it. ## This cell initializes Python so that datascience, numpy and scipy packages ␣ , → are ready to use. from datascience import * % matplotlib inline import matplotlib.pyplot as plots plots . style . use( 'fivethirtyeight' ) import numpy as np import scipy.stats as stats from IPython.core.display import display, HTML toggle_code_str = ''' <form action="javascript:code_toggle()"><input type="submit" id="toggleButton" ␣ , → value="Hide/Show Code (Too Advanced or Not the Point)"></form> ''' toggle_code_prepare_str = ''' <script> function code_toggle() { if ($('div.cell.code_cell.rendered.selected div.input').css('display')! , → ='none'){ $('div.cell.code_cell.rendered.selected div.input').hide(); } else { $('div.cell.code_cell.rendered.selected div.input').show(); } } </script> ''' display(HTML(toggle_code_prepare_str + toggle_code_str)) def hide_code (): 1

display(HTML(toggle_code_str)) <IPython.core.display.HTML object> 1.2 The groupstats function [33]: ## Do not change this cell, only execute it. ## This cell creates the function `groupstats` which provides descriptive ␣ , → statistics ## on a numeric variable for each level of a grouping variable. def groupstats (table, group, data): ### This function will find all the major descriptive stats you need ### cut = table . select(group, data) . sort(group) favstats = cut . group(group, np . mean) . sort(group) words = [data, 'mean' ] favstats = favstats . relabeled( ' ' . join(words), "mean" ) groups = favstats . column( 0 ) q1 = make_array() for i in np . arange( len (groups)): q1 = np . append(q1, np . percentile(table . where(group, groups . item(i)) . , → column(data), 25 )) q3 = make_array() for i in np . arange( len (groups)): q3 = np . append(q3, np . percentile(table . where(group, groups . item(i)) . , → column(data), 75 )) favstats = favstats . with_column( 'std' , cut . group(group, stats . tstd) . , → sort(group) . column( 1 ) ) favstats = favstats . with_column( 'min' , cut . group(group, min ) . sort(group) . , → column( 1 ) ) favstats = favstats . with_column( 'Q1' , q1 ) favstats = favstats . with_column( 'median' , cut . group(group, np . median) . , → sort(group) . column( 1 ) ) favstats = favstats . with_column( 'Q3' , q3 ) favstats = favstats . with_column( 'max' , cut . group(group, max ) . sort(group) . , → column( 1 ) ) favstats = favstats . with_column( 'IQR' , cut . group(group, stats . iqr) . , → sort(group) . column( 1 ) ) favstats = favstats . with_column( 'n' , cut . group(group ) . sort(group) . , → column( 1 ) ) return favstats from hide_code3 import hide_code 2

[34]: Sleep position | Year mean | Extraversion mean | Number of textees mean | Hours of sleep mean | Handedness mean On your back | | 5.57947 | 6.60596 | 7.11175 | On your left side | | 5.66845 | 7.46791 | 7.00535 | On your right side | | 5.89401 | 7.50922 | 7.05645 | On your stomach | | 5.96226 | 7.58491 | 7.15094 | 8 np.tstd standard deviation Standard Deviation (SD) is the square root of the variance sd = variance ** 0.5 stats.tstd(values) WARNING: np.std computes the population standard deviation, not the sample standard deviation. 9 np.percentile use the np.percentile command to find the 50￿￿ percentile (the median) of a short data set. The Interquartile Range The ￿￿￿=￿3−￿1 10 np.average returns the mean value of an array Ex: np.average(sf.column(‘height’)) outputs: the average (226.470) 11 np.arange shows the number of values you specify from that array [35]: #Ex: make_array( 0 , 1 , 2 , 3 , 4 , 5 , 6 ) np . arange( 6 ) [35]: array([0, 1, 2, 3, 4, 5]) [36]: #Ex 2 np . arange( 1 , 21 , 2 ) [36]: array([ 1, 3, 5, 7, 9, 11, 13, 15, 17, 19]) 4

[37]: #Ex 3 np . arange( 15 , 7 , -1 ) [37]: array([15, 14, 13, 12, 11, 10, 9, 8]) 12 .take a copy of the original table with only the rows at the given indices 13 .group Group rows by unique values or combinations of values in a column(s) output: new table [38]: survey = Table . read_table( 'welcome_survey_v4.csv' ) survey . group( 'Sleep position' ) [38]: Sleep position | count On your back | 302 On your left side | 374 On your right side | 434 On your stomach | 212 14 .pivot A table where each distinct value in column 1 has its own column and each unique value in column 2 has its own row. [39]: #Example: survey . pivot( 'Sleep position' , 'Handedness' ) /opt/conda/lib/python3.8/site-packages/datascience/tables.py:920: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray values = np.array(tuple(values)) [39]: Handedness | On your back | On your left side | On your right side | On your stomach Both | 4 | 5 | 7 | 1 Left-handed | 31 | 27 | 30 | 12 Right-handed | 267 | 342 | 397 | 199 5

19 are.between, are. containing, are.equal_to ex: - movies.where(‘Year’, are.between(2000, 2005)) • movies.where(‘#1 Movie’, are.containing(‘Harry Potter’)) • movies.where(‘Year’, are.equal_to(2002)) 20 Functions of Arrays Make_array: Makes a numpy array with the values passed in (can be numbers or words, but not both together) len(‘array name’): tells the length of that array Sum(array): returns the sum of values in that array etc… [42]: #example my_array = make_array( 1 , 2 , 3 , 4 ) my_array [42]: array([1, 2, 3, 4]) 21 Graphs [43]: #BAR GRAPH EX: top_movies = Table . read_table( 'top_movies_2017.csv' ) studios = top_movies . select( 'Studio' ) studios studio_distribution = studios . group( 'Studio' ) #actual code to get bar graph studio_distribution . barh( 'Studio' ) 7

8

23 Boxplots Box plots are a graphical display of the descriptive statistics that we know as the Five Number Summary. Five Number Summary is as follows • The minimum • The 25￿￿ percentile, ￿1 • The 50￿￿ percentile, the median • The 75￿￿ percentile, ￿3 • The maximum [46]: #EXAMPLE pets = make_array( 4 , 2 , 4 , 1 , 2 , 6 , 1 , 0 , 1 , 3 , 2 , 4 , 10 , 1 , 2 , 4 , 12 , 3 , 1 , 3 , ␣ , → 4 , 0 , 0 ) plots . boxplot(pets, widths =0.4 ); plots . xlabel( "class pets" ); 10

24 .plot Draws a line graph consisting of one point for each row of the table. Example: everyone.plot(‘AGE’, ‘2010’) output: would make a line plot graph that shows the age in year 2010. (yr = y axis age = x axis) 11