Data Manipulation with pandas

# Add your code snippets here

# Add total col as sum of individuals and family_members
homelessness["total"] = homelessness["individuals"] + homelessness["family_members"]

# Add p_individuals col as proportion of total that are individuals
homelessness["p_individuals"] = homelessness["individuals"]/ homelessness["total"]

# See the result
print(homelessness)

# Count the number of stores of each type
store_counts = store_types["type"].value_counts()
print(store_counts)
#======================================================================
# Get the proportion of stores of each type
store_props = store_types["type"].value_counts(normalize=True)
print(store_props)

# Count the number of each department number and sort
dept_counts_sorted = store_depts["department"].value_counts(sort=True)
print(dept_counts_sorted)

# Get the proportion of departments of each number and sort
dept_props_sorted = store_depts["department"].value_counts(sort=True, normalize=True)
print(dept_props_sorted)

#====================================================================================
# Import numpy with the alias np
import numpy as np

# For each store type, aggregate weekly_sales: get min, max, mean, and median
sales_stats = sales_stats = sales.groupby("type")["weekly_sales"].agg([np.min, np.max, np.mean, np.median])

# Print sales_stats
print(sales_stats)

# For each store type, aggregate unemployment and fuel_price_usd_per_l: get min, max, mean, and median
unemp_fuel_stats = sales.groupby("type")[["unemployment", "fuel_price_usd_per_l"]].agg([np.min, np.max, np.mean, np.median])
# Print unemp_fuel_stats
print(unemp_fuel_stats)

#===========================================================================================
# Subset rows from India, Hyderabad to Iraq, Baghdad
print(temperatures_srt.loc[("India", "Hyderabad"):("Iraq", "Baghdad")])

# Subset columns from date to avg_temp_c
print(temperatures_srt.loc[:, "date":"avg_temp_c"])

# Subset in both directions at once
print(temperatures_srt.loc[("India", "Hyderabad"):("Iraq", "Baghdad"), "date":"avg_temp_c"])

#============================================================================================

# Use Boolean conditions to subset temperatures for rows in 2010 and 2011
temperatures_bool = temperatures[(temperatures["date"] >= "2010-01-01") & (temperatures["date"] <= "2011-12-31")]
print(temperatures_bool)

# Set date as the index and sort the index
temperatures_ind = temperatures.set_index("date").sort_index()

# Use .loc[] to subset temperatures_ind for rows in 2010 and 2011
print(temperatures_ind.loc["2010":"2011"])

# Use .loc[] to subset temperatures_ind for rows from Aug 2010 to Feb 2011
print(temperatures_ind.loc["2010-08":"2011-02"])

#============================================================================================
# Get the worldwide mean temp by year
mean_temp_by_year = temp_by_country_city_vs_year.mean()

# Filter for the year that had the highest mean temp
print(mean_temp_by_year[mean_temp_by_year == mean_temp_by_year.max()])

# Get the mean temp by city
mean_temp_by_city = temp_by_country_city_vs_year.mean(axis="columns")

# Filter for the city that had the lowest mean temp
print(mean_temp_by_city[mean_temp_by_city == mean_temp_by_city.min()])

#=======================================================================
# Scatter plot of avg_price vs. nb_sold with title
avocados.plot(x = "nb_sold", y= "avg_price", kind= "scatter", title= "Number of avocados sold vs. average price")

# Show the plot
plt.show()

#============================================================================

# Modify bins to 20
avocados[avocados["type"] == "conventional"]["avg_price"].hist(bins=20)

# Modify bins to 20
avocados[avocados["type"] == "organic"]["avg_price"].hist(bins=20)

# Add a legend
plt.legend(["conventional", "organic"])

# Show the plot
plt.show()