Lab-05 - Jupyter Notebook

Part 1: Data Visualizations 1. Grouped Bar Plots: Make both a side-by-side bar plot and a stacked bar plot that displays the number of child visitors and the number of adult visitors at a waterpark in the months of April, May, June and July. Be sure to include titles, legends and appropriate labels sufficiently sized for readability. April Children: 780 Adults: 315 May Children: 1050 Adults: 400 June Children: 3056 Adults: 1000 July Children: 5025 Adults: 1500 In [179]:  import numpy as np import matplotlib.pyplot as plt

In [180]:  children = ( 780 , 1050 , 3056 , 5025 ) ind = np.arange( 4 ) width = 0.35 fig, ax = plt.subplots() rects1 = ax.bar(ind, children, width) adult = ( 315 , 400 , 1000 , 1500 ) rects2 = ax.bar(ind + width, adult, width) ax.set_ylabel( 'Number of Visitors' ,fontsize = 13 ) ax.set_title( 'Number of Vistors in 4months(April - July)' ,fontsize = 13 ) ax.set_xticks(ind + width / 2 ) ax.set_xticklabels(( 'April' , 'May' , 'June' , 'July' ),fontsize = 10 ) ax.legend((rects1[ 0 ], rects2[ 0 ]), ( 'children' , 'adult' )) def autolabel (rects): for rect in rects: height = rect.get_height() ax.text(rect.get_x() + rect.get_width() / 2. , height, '%d' % int (height),ha = 'center' , va = 'bottom' ) autolabel(rects1) autolabel(rects2) plt.show()

2. Histogram: Make a histogram of the following scores from the Fall 2017 Data Structures course at Loyola University Chicago. Feel free to experiment on the best number of histogram bins for visualization. 114.8, 98.8, 97.3, 96, 94.1, 93.1, 93.1, 91.6, 91.5, 91.3, 90.3, 89.2, 87.5, 87.4, 85.2, 81.7, 81.6, 81.5, 80, 79.3, 78.2, 77.6, 77.1, 76.7, 75.1, 73.9, 72, 71, 64.6, 63.3, 47.2, 38.7 In [182]:  In [129]:  38.7 Fall_2017 = np.array([ 114.8 , 98.8 , 97.3 , 96 , 94.1 , 93.1 , 93.1 , 91.6 , 91.5 , 91.3 , 90.3 , 89.2 , 87.5 , 87.4 , 85.2 , 81.7 , 81.6 , 81.5 , 80 , 79.3 , 78.2 , 77.6 , 77.1 , 76.7 , 75.1 , 73.9 , 72 , 71 , 64.6 , 63.3 , 47.2 , 38.7 ] print ( min (Fall_2017))

In [130]:  In [131]:  114.8 Out[131]: Text(0.5, 1.0, 'Fall 2017- Data Structures Course Scrores ') print ( max (Fall_2017)) t = [ 0 , 20 , 30 , 40 , 50 , 60 , 70 , 80 , 90 , 100 , 110 , 120 ] plt.hist(Fall_2017,bins = t,ec = "black" ,color = 'green' ) plt.xticks(t) plt.xlabel( "scores" ) plt.ylabel( "count" ) plt.grid(axis = 'y' , linestyle = '--' , alpha = 0.6 ) plt.title( "Fall 2017- Data Structures Course Scrores " )

In [132]:  Using the same info as above, make a subplot with 2 different graphs- one graph for sin(x) and Out[132]: <matplotlib.legend.Legend at 0x184f1b56410> x = np.arange( - 2 * np.pi, 2 * np.pi,np.pi / 4 ) y = np.sin(x) z = np.cos(x + np.pi / 2 ) plt.plot(x,y,color = 'red' ,label = "sin(x)" ) plt.plot(x,z,color = 'green' ,label = "cos(x+π/2)" ) plt.xlabel( '-2π to 2π' ) plt.ylabel( 'sin(x) and cos(x+ π/2)' ) plt.title( 'sin(x) and cos(x+ π/2) line plot' ) plt.grid( True ) plt.legend()

In [133]:  4. Scatter Plot: Using the following data about winter temperatures affecting the number of days for lake ice at Lake Superior, construct a scatter plot to display the data. Include a line of best fit. plt.figure(figsize = ( 10 , 4 )) plt.subplot( 1 , 2 , 1 ) plt.plot(x, y, color = 'red' , label = 'sin(x)' ) plt.xlabel( 'x' ) plt.ylabel( 'Value' ) plt.title( 'sin(x)' ) plt.subplot( 1 , 2 , 2 ) plt.plot(x, z, color = 'green' , label = 'cos(x + π/2)' ) plt.xlabel( 'x' ) plt.ylabel( 'Value' ) plt.title( 'cos(x + π/2)' ) plt.tight_layout() plt.show()

In [134]:  import numpy as np import matplotlib.pyplot as plt from scipy import stats mean_temperature = [ 22.94 , 23.02 , 25.68 , 19.96 , 24.80 , 23.98 , 22.10 , 20.30 , 24.20 , 22.74 , 24.16 , 24.94 , 22.40 , 22.14 , 20.84 , 25.66 , 21.73 , 24.49 , 24.13 , 22.17 , 21.73 , 20.41 , 24.41 , 23.95 , 20.95 , 26.71 , 22.81 , 23.11 , 23.33 , 28.83 , 23.11 , 21.47 , 23.97 , 24.75 , 23.61 , 23.08 , 21.24 , 26.63 , 23.88 ] days_of_ice = [ 87 , 137 , 106 , 97 , 105 , 118 , 118 , 136 , 91 , 107 , 96 , 114 , 125 , 115 , 118 , 82 , 115 , 97 , 104 , 146 , 126 , 141 , 111 , 123 , 118 , 83 , 48 , 118 , 116 , 81 , 116 , 123 , 112 , 99 , 102 , 118 , 63 , 62 , 132 ] slope, intercept, r_value, p_value, std_err = stats.linregress(mean_temperature, days_of_ice) line = slope * np.array(mean_temperature) + intercept plt.figure(figsize = ( 10 , 6 )) plt.scatter(mean_temperature, days_of_ice, label = 'Data Points' , color = 'blue' ) plt.plot(mean_temperature, line, label = 'Line of Best Fit' , color = 'red' ) plt.xlabel( 'Mean Temperature (Fahrenheit)' ) plt.ylabel( 'Days of Ice' ) plt.title( 'Relationship between Mean Temperature and Days of Ice' ) plt.legend() plt.grid( True ) plt.show()

Part 2: Basic Data Structure 1: Lists 1. Make a list with the spelled-out number strings ‘one’, ‘two’, ‘three’, ‘four’, and ‘five’ in that order and call it myList.

6. Create a list only of the lengths of the strings and show your result. You can use the loop before to fill the list. In [140]:  2: Dictionaries 1. Make a dictionary with the keys be English words as below, and the values be the translation. You can use this language example (German) or choose your own. Note: you need to make sure all of these words are represented as strings, in quotes. apple - Apfel apples - Äpfel I - Ich and - und like - mag strawberries - Erdbeeren In [141]:  2. Use the dictionary to look up the translation for ‘apple’ and ‘like’. In [142]:  3. Make a variable var with the string “I like apples and strawberries”. In [143]:  Out[140]: [3, 3, 4, 4, 3] Out[141]: {'apple': 'Apfel', 'apples': 'Äpfel', 'I': 'Ich', 'and': 'und', 'like': 'mag', 'strawberries': 'Erdbeeren'} Apfel mag Out[143]: 'I like apples and strawberries' length_string = [ len (word) for word in myList] length_string dictionary_words = { "apple" : "Apfel" , "apples" : "Äpfel" , "I" : "Ich" , "and" : "und" , "like" : "mag" , "strawberries" : "Erdbeeren" } dictionary_words print (dictionary_words[ "apple" ]) print (dictionary_words[ "like" ]) var = "I like apples and strawberries" var

4. Now create a list from var with each word a separate item (this is a string split operation). In [144]:  5. Iterate through the list you’ve created and replace any word in your dictionary with the translation. In [145]:  6. Now take your new list and turn it into a string with spaces between the words. In [146]:  3: Arrays 1. Create an array of zeros of size 8 x 8 and print the data type of the array. Out[144]: ['I', 'like', 'apples', 'and', 'strawberries'] Out[145]: ['Ich', 'mag', 'Äpfel', 'und', 'Erdbeeren'] Out[146]: 'Ich mag Äpfel und Erdbeeren' split_string = var.split() split_string replace_list = [] for item in split_string: if item in dictionary_words: replace_list.append(dictionary_words[item]) else : replace_list.append(item) replace_list replace_string = ' ' .join(replace_list) replace_string

In [150]:  4. Print only the top 4 rows and columns. In [151]:  5. Make a 1D array out of your 2D array with the numbers 1 to 64 in order (note the column vs row issue, you may need transposes.) In [152]:  In [153]:  6. Now take that 1D array you made from before and reshape it back to the original 2D array. Out[150]: array([[ 1, 9, 17, 25, 33, 41, 49, 57], [ 2, 10, 18, 26, 34, 42, 50, 58], [ 3, 11, 19, 27, 35, 43, 51, 59], [ 4, 12, 20, 28, 36, 44, 52, 60], [ 5, 13, 21, 29, 37, 45, 53, 61], [ 6, 14, 22, 30, 38, 46, 54, 62], [ 7, 15, 23, 31, 39, 47, 55, 63], [ 8, 16, 24, 32, 40, 48, 56, 64]]) Out[151]: array([[ 1, 9, 17, 25], [ 2, 10, 18, 26], [ 3, 11, 19, 27], [ 4, 12, 20, 28]]) Out[152]: array([ 1, 9, 17, 25, 33, 41, 49, 57, 2, 10, 18, 26, 34, 42, 50, 58, 3, 11, 19, 27, 35, 43, 51, 59, 4, 12, 20, 28, 36, 44, 52, 60, 5, 13, 21, 29, 37, 45, 53, 61, 6, 14, 22, 30, 38, 46, 54, 62, 7, 15, 23, 31, 39, 47, 55, 63, 8, 16, 24, 32, 40, 48, 56, 64]) Out[153]: 1 array = np.transpose(fill_array) array array[ 0 : 4 , 0 : 4 ] array_1 = array.flatten() array_1 array_1.ndim

In [154]:  In [155]:  4: Application - Word Counts Word counts are often used in text processing to automatically classify documents by topic. They are also used to automatically measure the “sentiment” by counting, for example, the number of positive or negative words used in the comment or essay. Write code to count the number of unique words in a very large string using the following steps. A) First convert the string to a list with each word a separate item in the list. Hint: use a string split function for your language, and make sure it separates by “ ”. B) Then use a dictionary to associate each word with a count. Note, the dictionary won’t be able to increment a key unless you add it first, so you may have to check to see if it exists before setting the original count of a word to 1. C) Print each word and its count afterwards, and test with an interesting block of text that will have multiple words counted multiple times. (Note, the words don’t have to be in any particular order.) For example: “how much wood would a woodchuck chuck if a woodchuck could chuck wood” Expected output: how - 1 much -1 wood - 2 would - 1 a - 2 woodchuck - 2 chuck - 2 if - 1 could - 1 In [156]:  Out[154]: array([[ 1, 9, 17, 25, 33, 41, 49, 57], [ 2, 10, 18, 26, 34, 42, 50, 58], [ 3, 11, 19, 27, 35, 43, 51, 59], [ 4, 12, 20, 28, 36, 44, 52, 60], [ 5, 13, 21, 29, 37, 45, 53, 61], [ 6, 14, 22, 30, 38, 46, 54, 62], [ 7, 15, 23, 31, 39, 47, 55, 63], [ 8, 16, 24, 32, 40, 48, 56, 64]]) Out[155]: 2 Out[156]: 'how much wood would a woodchuck chuck if a woodchuck could chuck wood' array_2 = array_1.reshape( 8 , 8 ) array_2 array_2.ndim Input_String = "how much wood would a woodchuck chuck if a woodchuck could chuck wood" Input_String

Part 3: Data Frames In this part, we will study a classic data set - the survivors in the sinking of the Titanic. As there were limited lifeboats, decisions were made prioritizing who would and would not survive. We will observe how different factors such as age, sex, and class affected a person’s chance of survival using data frames. Steps: 1. Input the following data into a data frame called titanic, and display the entire data frame: Sex, Class, Survived, Died Children, First, 6, 0 Children, Second, 24, 0 Children, Third, 27, 52 Men, First, 57, 118 Men, Second, 14, 154 Men, Third, 75, 387 Men, Crew, 192, 693 Women, First, 140, 4 Women, Second, 80, 13 Women, Third, 76, 89 Women, Crew, 20, 3

In [159]:  2. Now only show the data of the people in first class. In [160]:  3. Delete the crew members from the data. Out[159]: Sex Class Survived Died 0 Children First 6 0 1 Children Second 24 0 2 Children Third 27 52 3 Men First 57 118 4 Men Second 14 154 5 Men Third 75 387 6 Men Crew 192 693 7 Women First 140 4 8 Women Second 80 13 9 Women Third 76 89 10 Women Crew 20 3 Out[160]: Sex Class Survived Died 0 Children First 6 0 3 Men First 57 118 7 Women First 140 4 import pandas as pd titanic_data = { 'Sex' : [ 'Children' , 'Children' , 'Children' , 'Men' , 'Men' , 'Men' , 'Men' , 'Women' , 'Women' , 'Women' , 'Women' ], 'Class' : [ 'First' , 'Second' , 'Third' , 'First' , 'Second' , 'Third' , 'Crew' , 'First' , 'Second' , 'Third' , 'Crew' ], 'Survived' : [ 6 , 24 , 27 , 57 , 14 , 75 , 192 , 140 , 80 , 76 , 20 ], 'Died' : [ 0 , 0 , 52 , 118 , 154 , 387 , 693 , 4 , 13 , 89 , 3 ] } data_frame = pd.DataFrame(titanic_data) data_frame data_frame.loc[data_frame[ "Class" ] == "First" ]