Skip to content

Intermediate Python

Run the hidden code cell below to import the data used in this course.

# Import the course packages
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Import the two datasets
gapminder = pd.read_csv("datasets/gapminder.csv")
brics = pd.read_csv("datasets/brics.csv")

Take Notes

Add notes about the concepts you've learned and code cells with code you want to keep.

# Import numpy as np
import numpy as np 
pop= [31.889923, 3.600523, 33.333216, 12.420476, 40.301927, 20.434176, 8.199783, 0.708573, 150.448339, 10.392226, 8.078314, 9.119152, 4.552198, 1.639131, 190.010647, 7.322858, 14.326203, 8.390505, 14.131858, 17.696293, 33.390141, 4.369038, 10.238807, 16.284741, 1318.683096, 44.22755, 0.71096, 64.606759, 3.80061, 4.133884, 18.013409, 4.493312, 11.416987, 10.228744, 5.46812, 0.496374, 9.319622, 13.75568, 80.264543, 6.939688, 0.551201, 4.906585, 76.511887, 5.23846, 61.083916, 1.454867, 1.688359, 82.400996, 22.873338, 10.70629, 12.572928, 9.947814, 1.472041, 8.502814, 7.483763, 6.980412, 9.956108, 0.301931, 1110.396331, 223.547, 69.45357, 27.499638, 4.109086, 6.426679, 58.147733, 2.780132, 127.467972, 6.053193, 35.610177, 23.301725, 49.04479, 2.505559, 3.921278, 2.012649, 3.193942, 6.036914, 19.167654, 13.327079, 24.821286, 12.031795, 3.270065, 1.250882, 108.700891, 2.874127, 0.684736, 33.757175, 19.951656, 47.76198, 2.05508, 28.90179, 16.570613, 4.115771, 5.675356, 12.894865, 135.031164, 4.627926, 3.204897, 169.270617, 3.242173, 6.667147, 28.674757, 91.077287, 38.518241, 10.642836, 3.942491, 0.798094, 22.276056, 8.860588, 0.199579, 27.601038, 12.267493, 10.150265, 6.144562, 4.553009, 5.447502, 2.009245, 9.118773, 43.997828, 40.448191, 20.378239, 42.292929, 1.133066, 9.031088, 7.554661, 19.314747, 23.174294, 38.13964, 65.068149, 5.701579, 1.056608, 10.276158, 71.158647, 29.170398, 60.776238, 301.139947, 3.447496, 26.084662, 85.262356, 4.018332, 22.211743, 11.746035, 12.311143]

gdp_cap=[974.5803384, 5937.029525999999, 6223.367465, 4797.231267, 12779.37964, 34435.367439999995, 36126.4927, 29796.04834, 1391.253792, 33692.60508, 1441.284873, 3822.137084, 7446.298803, 12569.85177, 9065.800825, 10680.79282, 1217.032994, 430.0706916, 1713.778686, 2042.09524, 36319.23501, 706.016537, 1704.063724, 13171.63885, 4959.114854, 7006.580419, 986.1478792, 277.5518587, 3632.557798, 9645.06142, 1544.750112, 14619.222719999998, 8948.102923, 22833.30851, 35278.41874, 2082.4815670000003, 6025.374752000001, 6873.262326000001, 5581.180998, 5728.353514, 12154.08975, 641.3695236000001, 690.8055759, 33207.0844, 30470.0167, 13206.48452, 752.7497265, 32170.37442, 1327.60891, 27538.41188, 5186.050003, 942.6542111, 579.2317429999999, 1201.637154, 3548.3308460000003, 39724.97867, 18008.94444, 36180.78919, 2452.210407, 3540.651564, 11605.71449, 4471.061906, 40675.99635, 25523.2771, 28569.7197, 7320.880262000001, 31656.06806, 4519.461171, 1463.249282, 1593.06548, 23348.139730000003, 47306.98978, 10461.05868, 1569.331442, 414.5073415, 12057.49928, 1044.770126, 759.3499101, 12451.6558, 1042.581557, 1803.151496, 10956.99112, 11977.57496, 3095.7722710000003, 9253.896111, 3820.17523, 823.6856205, 944.0, 4811.060429, 1091.359778, 36797.93332, 25185.00911, 2749.320965, 619.6768923999999, 2013.977305, 49357.19017, 22316.19287, 2605.94758, 9809.185636, 4172.838464, 7408.905561, 3190.481016, 15389.924680000002, 20509.64777, 19328.70901, 7670.122558, 10808.47561, 863.0884639000001, 1598.435089, 21654.83194, 1712.472136, 9786.534714, 862.5407561000001, 47143.17964, 18678.31435, 25768.25759, 926.1410683, 9269.657808, 28821.0637, 3970.095407, 2602.394995, 4513.480643, 33859.74835, 37506.41907, 4184.548089, 28718.27684, 1107.482182, 7458.396326999999, 882.9699437999999, 18008.50924, 7092.923025, 8458.276384, 1056.380121, 33203.26128, 42951.65309, 10611.46299, 11415.80569, 2441.576404, 3025.349798, 2280.769906, 1271.211593, 469.70929810000007]

life_exp=[43.828, 76.423, 72.301, 42.731, 75.32, 81.235, 79.829, 75.635, 64.062, 79.441, 56.728, 65.554, 74.852, 50.728, 72.39, 73.005, 52.295, 49.58, 59.723, 50.43, 80.653, 44.74100000000001, 50.651, 78.553, 72.961, 72.889, 65.152, 46.462, 55.322, 78.782, 48.328, 75.748, 78.273, 76.486, 78.332, 54.791, 72.235, 74.994, 71.33800000000001, 71.878, 51.57899999999999, 58.04, 52.947, 79.313, 80.657, 56.735, 59.448, 79.406, 60.022, 79.483, 70.259, 56.007, 46.388000000000005, 60.916, 70.19800000000001, 82.208, 73.33800000000001, 81.757, 64.69800000000001, 70.65, 70.964, 59.545, 78.885, 80.745, 80.546, 72.567, 82.603, 72.535, 54.11, 67.297, 78.623, 77.58800000000001, 71.993, 42.592, 45.678, 73.952, 59.443000000000005, 48.303, 74.241, 54.467, 64.164, 72.801, 76.195, 66.803, 74.543, 71.164, 42.082, 62.069, 52.906000000000006, 63.785, 79.762, 80.204, 72.899, 56.867, 46.859, 80.196, 75.64, 65.483, 75.53699999999999, 71.752, 71.421, 71.688, 75.563, 78.098, 78.74600000000001, 76.442, 72.476, 46.242, 65.528, 72.777, 63.062, 74.002, 42.568000000000005, 79.972, 74.663, 77.926, 48.159, 49.339, 80.941, 72.396, 58.556, 39.613, 80.884, 81.70100000000001, 74.143, 78.4, 52.517, 70.616, 58.42, 69.819, 73.923, 71.777, 51.542, 79.425, 78.242, 76.384, 73.747, 74.249, 73.422, 62.698, 42.38399999999999, 43.487]


# Store pop as a numpy array: np_pop
np_pop = np.array(pop)
# Double np_pop
np_pop = np_pop*2

# Update: set s argument to np_pop
plt.scatter(gdp_cap, life_exp, s = np_pop, alpha=0.8)

# Previous customizations
plt.xscale('log') 
plt.xlabel('GDP per Capita [in USD]')
plt.ylabel('Life Expectancy [in years]')
plt.title('World Development in 2007')
plt.xticks([1000, 10000, 100000],['1k', '10k', '100k'])
plt.text(1550, 71, 'India')
plt.text(5700, 80, 'China')

# Display the plot
plt.show()

Add your notes here

# Add your code snippets here

Explore Datasets

Use the DataFrames imported in the first cell to explore the data and practice your skills!

  • Create a loop that iterates through the brics DataFrame and prints "The population of {country} is {population} million!".
  • Create a histogram of the life expectancies for countries in Africa in the gapminder DataFrame. Make sure your plot has a title, axis labels, and has an appropriate number of bins.
  • Simulate 10 rolls of two six-sided dice. If the two dice add up to 7 or 11, print "A win!". If the two dice add up to 2, 3, or 12, print "A loss!". If the two dice add up to any other number, print "Roll again!".
import pandas as pd

# Build cars DataFrame
names = ['United States', 'Australia', 'Japan', 'India', 'Russia', 'Morocco', 'Egypt']
dr =  [True, False, False, False, True, True, True]
cpc = [809, 731, 588, 18, 200, 70, 45]
cars_dict = { 'country':names, 'drives_right':dr, 'cars_per_cap':cpc }
cars = pd.DataFrame(cars_dict)

# Definition of row_labels
row_labels = ['US', 'AUS', 'JPN', 'IN', 'RU', 'MOR', 'EG']

# Specify row labels of cars
cars.index = row_labels

# Print cars again
print(cars)

# Print out country column as Pandas Series
print(cars['country'])

# Print out country column as Pandas DataFrame
print(cars[['country']])

# Print out DataFrame with country and drives_right columns
print(cars[['country', 'drives_right']]) 

# Print out first 3 observations
print(cars[0:3])

# Print out fourth, fifth and sixth observation
print(cars[3:6])

# With loc and iloc you can do practically any data selection operation on DataFrames you can think of. loc is label-based, which means that you have to specify rows and columns based on their row and column labels. iloc is integer index based, so you have to specify rows and columns by their integer index like you did in the previous exercise.

#Print out observation for Japan
print(cars.loc[['JPN']])
print(cars.iloc[[4]])

# Print out observations for Australia and Egypt
print(cars.loc[['AUS', 'EG']])
print(cars.iloc[[2, 7]])


# Print out drives_right value of Morocco
print(cars.loc['MOR', 'drives_right'])

# Print sub-DataFrame
print(cars.iloc[[4,5],[1, 2]])
Run cancelled
#while loops. Creating the inverted pendulum 
offset = 8 
while offset != 0: 
    offset = offset - 1
    print('correcting...')
    print(offset)
Run cancelled
#while usin IF- ESLE statements
# Initialize offset
offset = -6

# Code the while loop
while offset != 0 :
    print("correcting...")
    if offset > 0 :
      offset = offset - 1
    else : 
      offset = offset + 1   
    print(offset)
Run cancelled
#for loop 
# areas list
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

# Code the for loop
for ft in areas:
   print(ft)
Run cancelled
# areas list
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

# Change for loop to use enumerate() and update print()
for index, area in enumerate(areas) :
    print("room " + str(index) + ": " + str(area))
Run cancelled
#For non-programmer folks, room 0: 11.25 is strange. Wouldn't it be better if the count started at 1?
# areas list
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

# Code the for loop
for index, area in enumerate(areas) :
    print("room " + str(index + 1) + ": " + str(area))
Run cancelled
# house list of lists
house = [["hallway", 11.25], 
         ["kitchen", 18.0], 
         ["living room", 20.0], 
         ["bedroom", 10.75], 
         ["bathroom", 9.50]]
         
# Build a for loop from scratch
for x, y in house:
    print("the " + str(x)+ " is " + str(y) + " sqm")
Run cancelled
# Definition of dictionary (for loop examples) #For 2D array use np.nditer(np_array)
europe = {'spain':'madrid', 'france':'paris', 'germany':'berlin',
          'norway':'oslo', 'italy':'rome', 'poland':'warsaw', 'austria':'vienna' }
          
# Iterate over europe
for key, value in europe.items():
    print("the capital of " + key + " " + "is " + str(value))
‌
‌
‌