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.

Add your notes here

# 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)
    
#For Loops    
# 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))

#Wrong Code --
# 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 enumerate(house) :
    print("the " + x[0] + " " + y[0] + " is " + str(y[1]) + " sqm")
    
#Correct Code --
# 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 in house :
    print("the " + x[0] + " is " + str(x[1]) + " sqm")
#-----------------------------------------------------------------------------------------------------------    
# Definition of dictionary
europe = {'spain':'madrid', 'france':'paris', 'germany':'berlin',
          'norway':'oslo', 'italy':'rome', 'poland':'warsaw', 'austria':'vienna' }
          
# Iterate over europe
#world = { "afghanistan":30.55, 
#          "albania":2.77,
#          "algeria":39.21 }

# exercise -- for key, value in europe.items() :
#    print(key + " -- " + str(value))
    
for key, value in europe.items() :
    print("the capital of " + key + " is " + str(value))
    
#------------------------------------------------------------------------------------------------------------    
# Import numpy as np
import numpy as np

# For loop over np_height
#np_height = np.array([73, 1.68, 1.71, 1.89, 1.79])
#x = np.array([np_height])
for x in np_height:
    print(str(x) + " inches ")

# For loop over np_baseball
for x in np.nditer(np_baseball):
    print(str(x))
#-------------------------------------------------------------------------------------------------------------
#Add column (2)

# Import cars data
import pandas as pd
cars = pd.read_csv('cars.csv', index_col = 0)

# Use .apply(str.upper)
cars["COUNTRY"] = cars["country"].apply(str.upper)

#------------------------------------------------------------------------------------------------------#
# Import numpy and set seed
import numpy as np
np.random.seed(123)

# Use randint() to simulate a dice
print(np.random.randint(1,7))

# Use randint() again
print(np.random.randint(1,7))
#-------------------------------------------------------------------------------------------------------#
# - Random Walk - my script

# NumPy is imported, seed is set

# Initialize random_walk
random_walk = [0]

# Complete the ___
for x in range(100) :
    # Set step: last element in random_walk
    step = random_walk[-1]

    # Roll the dice
    dice = np.random.randint(1,7)

    # Determine next step
    if dice <= 2:
        # step = step - 1
        step = max(0, step - 1) # updated version that allows dice to go below 0
    elif dice <= 5:
        step = step + 1
    else:
        step = step + np.random.randint(1,7)

    # append next_step to random_walk
    random_walk.append(step)
    
    # Import matplotlib.pyplot as plt
import matplotlib.pyplot as plt

# Plot random_walk
plt.plot(random_walk)

# Show the plot
plt.show()

# Print random_walk

#    print(random_walk) # correct answer
    
#    print(dice)
    
#    print(step)

#-------------------------------------------------------------------------------------------------------#

# NumPy is imported; seed is set

# Initialize all_walks (don't change this line)
all_walks = []

# Simulate random walk five times
for i in range(5) :

    # Code from before
    random_walk = [0]
    for x in range(100) :
        step = random_walk[-1]
        dice = np.random.randint(1,7)

        if dice <= 2:
            step = max(0, step - 1)
        elif dice <= 5:
            step = step + 1
        else:
            step = step + np.random.randint(1,7)
        random_walk.append(step)

    # Append random_walk to all_walks
    all_walks.append(random_walk)

# Print all_walks
print(all_walks)

#-------------------------------------------------------------------------------------------------------#

# numpy and matplotlib imported, seed set

# clear the plot so it doesn't get cluttered if you run this many times
plt.clf()

# Simulate random walk 20 times
all_walks = []
for i in range(20) :
    random_walk = [0]
    for x in range(100) :
        step = random_walk[-1]
        dice = np.random.randint(1,7)
        if dice <= 2:
            step = max(0, step - 1)
        elif dice <= 5:
            step = step + 1
        else:
            step = step + np.random.randint(1,7)

        # Implement clumsiness
        if ___ :
            step = 0

        random_walk.append(step)
    all_walks.append(random_walk)

# Create and plot np_aw_t
np_aw_t = np.transpose(np.array(all_walks))
plt.plot(np_aw_t)
plt.show()

#-------------------------------------------------------------------------------------------------------#

# numpy and matplotlib imported, seed set

# clear the plot so it doesn't get cluttered if you run this many times
plt.clf()

# Simulate random walk 20 times
all_walks = []
for i in range(20) :
    random_walk = [0]
    for x in range(100) :
        step = random_walk[-1]
        dice = np.random.randint(1,7)
        if dice <= 2:
            step = max(0, step - 1)
        elif dice <= 5:
            step = step + 1
        else:
            step = step + np.random.randint(1,7)

        # Implement clumsiness
        if np.random.rand() <= 0.005 :
            step = 0

        random_walk.append(step)
    all_walks.append(random_walk)

# Create and plot np_aw_t
np_aw_t = np.transpose(np.array(all_walks))
plt.plot(np_aw_t)
plt.show()

#-------------------------------------------------------------------------------------------------------#

# Final Result

# numpy and matplotlib imported, seed set
import numpy as np
import matplotlib.pyplot as plt

# Simulate random walk 500 times
all_walks = []
for i in range(500) :
    random_walk = [0]
    for x in range(100) :
        step = random_walk[-1]
        dice = np.random.randint(1,7)
        if dice <= 2:
            step = max(0, step - 1)
        elif dice <= 5:
            step = step + 1
        else:
            step = step + np.random.randint(1,7)
        if np.random.rand() <= 0.001 :
            step = 0
        random_walk.append(step)
    all_walks.append(random_walk)

# Create and plot np_aw_t
np_aw_t = np.transpose(np.array(all_walks))

# Select last row from np_aw_t: ends
ends = np_aw_t[60,:]

# Plot histogram of ends, display plot
plt.hist(ends)
plt.show()

#-------------------------------------------------------------------------------------------------------#

# Intro to importing data in python.

# Open a file: file
file = open('moby_dick.txt', mode='r')

# Print it
print(file.read())

# Check whether file is closed
print(file.closed)

# Close file
file.close()

# Check whether file is closed
print(file.closed)

#-------------------------------------------------------------------------------------------------------#

# Reading the first three lines in a file's data.

# Read & print the first 3 lines
with open('moby_dick.txt') as file:
    print(file.readline())
    print(file.readline())
    print(file.readline())

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!".