Introduction to Statistics in Python

# Add your code snippets here

# Import numpy as np
import numpy as np

# Subset for Belgium and USA only
be_and_usa = food_consumption[(food_consumption['country'] == 'Belgium') | (food_consumption['country'] == 'USA')]

# Group by country, select consumption column, and compute mean and median
print(be_and_usa.groupby('country')['consumption'].agg([np.mean, np.median]))

# Import matplotlib.pyplot with alias plt
import matplotlib.pyplot as plt

# Subset for food_category equals rice
rice_consumption = food_consumption[food_consumption['food_category'] == 'rice']
print(rice_consumption)
# Histogram of co2_emission for rice and show plot
rice_consumption.co2_emission.hist()
plt.show()

# Subset for food_category equals rice
rice_consumption = food_consumption[food_consumption['food_category'] == 'rice']

# Calculate mean and median of co2_emission with .agg()
print(rice_consumption.agg([np.mean, np.median]))

# Calculate the quartiles of co2_emission
print(np.quantile(food_consumption['co2_emission'], [0, 0.25,0.5,0.75,1]))

#Calculate the six quantiles that split up the data into 5 pieces (quintiles) of the co2_emission column of food_consumption
print(np.quantile(food_consumption['co2_emission'], [0, 0.2, 0.4, 0.6, 0.8, 1]))

# Calculate the deciles of co2_emission
print(np.quantile(food_consumption['co2_emission'], [0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]))

# Print variance and sd of co2_emission for each food_category
print(food_consumption.groupby('food_category')['co2_emission'].agg([np.var, np.std]))

# Import matplotlib.pyplot with alias plt
import matplotlib.pyplot as plt

# Create histogram of co2_emission for food_category 'beef'
food_consumption[food_consumption['food_category'] == 'beef']['co2_emission'].hist()
# Show plot
plt.show()

# Create histogram of co2_emission for food_category 'eggs'
food_consumption[food_consumption['food_category']== 'eggs'] ['co2_emission'].hist()
# Show plot
plt.show()

# Calculate total co2_emission per country: emissions_by_country
emissions_by_country = food_consumption.groupby('country')['co2_emission'].sum()

print(emissions_by_country)

# Calculate total co2_emission per country: emissions_by_country
emissions_by_country = food_consumption.groupby('country')['co2_emission'].sum()

# Compute the first and third quartiles and IQR of emissions_by_country
q1 = np.quantile(emissions_by_country, 0.25)
q3 = np.quantile(emissions_by_country, 0.75)
iqr = q3-q1

# Calculate the lower and upper cutoffs for outliers
lower = q1 - 1.5 * iqr
upper = q3 + 1.5 * iqr

# Subset emissions_by_country to find outliers
outliers = emissions_by_country[(emissions_by_country < lower) | (emissions_by_country > upper)]
print(outliers)

# Count the deals for each product
counts = amir_deals['product'].value_counts()

# Calculate probability of picking a deal with each product
probs = counts/amir_deals.shape[0]
print(probs)