Intermediate Python for Data Science

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

year = [1950, 1970, 1990, 2010]
pop = [2.519, 3.69, 5.263, 6.972]

# line plot
plt.plot(year, pop)
plt.xlabel("Year")
plt.ylabel("Population (billion)")
plt.show()

# Scatter PLot
plt.scatter(year, pop)
plt.xlabel("Year")
plt.ylabel("Population (billion)")
plt.show()

data = pd.read_csv("data/worldpop.csv")

data.head()

pop = data["population"]
gdp = data["gdp_cap"]

# Line PLot
plt.plot(pop, gdp)
plt.xlabel("Population")
plt.ylabel("GDP")
plt.show()

# Scatter PLot
plt.scatter(pop, gdp)
plt.xlabel("Population")
plt.ylabel("Population (")
plt.show()

life_exp = data["life_exp"]

plt.title("Histogram with 15 bins")
plt.hist(life_exp, bins=15)
plt.show()

# to clean up plot
plt.clf()


plt.title("Histogram with 5 bins")
plt.hist(life_exp, bins=5)
plt.show()

# basic scatter
# Scatter plot
plt.scatter(gdp, life_exp)

# Previous customizations
plt.xscale('log') 
plt.xlabel('GDP per Capita [in USD]')
plt.ylabel('Life Expectancy [in years]')
plt.title('World Development in 2007')

# Definition of tick_val and tick_lab
tick_val = [1000, 10000, 100000]
tick_lab = ['1k', '10k', '100k']

# Adapt the ticks on the x-axis
plt.xticks(tick_val, tick_lab)

# After customizing, display the plot
plt.show()

# Definition of dictionary
europe = {'spain':'madrid', 'france':'paris', 'germany':'berlin', 'norway':'oslo' }

# Print out the keys in europe
print(europe.keys(), '\n')

# Print out value that belongs to key 'norway'
print(europe['norway'])

# 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]
dict = { 'country':names, 'drives_right':dr, 'cars_per_cap':cpc }
cars = pd.DataFrame(dict)
print(cars,"\n\n")

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

# Specify row labels of cars
cars.index = row_labels

# Print cars again
print(cars)

# to read data
brics = pd.read_csv("data/brics.csv", index_col = 0)

# to print data
print("Our brics dataset....\n")
print(brics, "\n\n")

# return pandas series
print("Printing pandas series...\n")
print(brics["country"], "\n\n")

# return pandas dataframe
print("Printing pandas dataframe...\n")
print(brics[["country"]],"\n\n")


# multiple dataframes
print("Printing multiple dataframes...\n")
print(brics[["country", "population"]],"\n\n")

# Multiple dataframes with index
print("Printing multiple dataframes with indexing...\n")
print(brics[1:4])

# Row access: loc
print("Row access pandas series\n")
print(brics.loc["IN"],"\n\n") 

print("Row access pandas dataframe\n")
print(brics.loc[["IN"]],"\n\n") 

print("Multple Row access\n")
print(brics.loc[["IN", "CH", "SA"]],"\n\n") 

print("Rows with specific column\n")
print(brics.loc[["RU", "IN","SA"], ["country", "capital"]])

# iloc

print("Row access pandas dataframe\n")
print(brics.iloc[[1]],"\n\n") 

print("Multple Row access\n")
print(brics.iloc[[1, 2, 4]],"\n\n") 

print("Rows with specific column\n")
print(brics.iloc[[1, 2, 4], :3])

my_house = np.array([18.0, 20.0, 10.75, 9.50])
your_house = np.array([14.0, 24.0, 14.25, 9.0])

# my_house greater than 18.5 or smaller than 10
print(np.logical_or(my_house > 18.5, my_house < 10))

# Both my_house and your_house smaller than 11

print(np.logical_and(my_house < 11, your_house < 11))
print(my_house)

cars = pd.read_csv('data/cars.csv', index_col = 0)

# Extract drives_right column as Series: dr
dr = cars["drives_right"]

# Use dr to subset cars: sel
sel = cars[dr]

# Print sel
print(sel)

# Create car_maniac: observations that have a cars_per_cap over 500
cpc = cars['cars_per_cap']
car_maniac = cpc > 500
print("Cars dataset more than 500 cars ..\n\n",cars[car_maniac])

between = np.logical_and(cpc > 100, cpc < 500)
medium = cars[between]
print("Cars dataset with cars between 100 and 500 cars per capital..\n\n", medium)

# while loop
x = 10
while x > 0:
    print("x is now: ", x)
    x = x - 2

# for loop

# areas list
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

for area in areas:
    print(area)
    
print("\nenumerate: looping with index\n")
for index, area in enumerate(areas):
    print("Area ", index, ": ", area)

# 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 room in house:
    print("the " + room[0] + " is " + str(room[1]) + " sqm" )

# iterate over dictionary

# Definition of dictionary
europe = {'spain':'madrid', 'france':'paris', 'germany':'berlin',
          'norway':'oslo', 'italy':'rome', 'poland':'warsaw', 'austria':'vienna' }
          
# Iterate over europe
for country, capital in europe.items():
    print("The capital of ", country, " is ", capital)

# looping over n dimensional numpy array

np_height = np.array([[23, 40, 55], [55, 90, 11]])

for height in np.nditer(np_height):
    print(height)

# looping over pandas dataframe

cars = pd.read_csv('data/cars.csv', index_col = 0)

# Iterate over rows of cars
for lab, row in cars.iterrows() :
    print(lab, ": ",row['cars_per_cap'] )

# adding new rows
cars["Name_lenght"] = cars['country'].apply(len)
print(cars)

np.random.seed(123)

random_walk = [0]

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

    if dice <= 2:
        # Replace below: use max to make sure step can't go below 0
        step = max(0,step - 1)
    elif dice <= 5:
        step = max(0, step + 1)
    else:
        step = max(0, step + np.random.randint(1,7))

    random_walk.append(step)

print(random_walk)

# visualization random walk
plt.plot(random_walk)
plt.title("Random walk")
plt.show()

# visualization random walk
plt.hist(random_walk, bins = 15)
plt.title("Random walk")
plt.show()

# Distribution

# initialize and populate all_walks
all_walks = []
for i in range(10) :
    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)
    all_walks.append(random_walk)

# Convert all_walks to Numpy array: np_aw
np_aw = np.array(all_walks)

# Plot np_aw and show
plt.plot(np_aw)
plt.show()

# Clear the figure
plt.clf()

# Transpose np_aw: np_aw_t
np_aw_t = np_aw.T

# Plot np_aw_t and show
plt.plot(np_aw_t)
plt.show()