Mexico_Housing_Insights

#groupby state and price_usd using mean price, sort descending
mean_price_by_state = df.groupby("state")["price_usd"].mean().sort_values(ascending=False)
mean_price_by_state

#bar plot using pandas, pandas can use plt functionalities as well
mean_price_by_state.plot(
    kind="bar",
    xlabel="State",
    ylabel="Price[USD]",
    title="Mean House Price by State"
);

#adding a new feature
df["price_per_m2"] = df["price_usd"] / df["area_m2"]

#use of groupby and plot together
mean_price_per_m2_by_state = (
    df.groupby("state")["price_per_m2"].mean().sort_values(ascending=False)
    .plot(
    kind="bar",
    xlabel="State",
    ylabel="price_per_m2",
    title="Mean House Price per m2 by State"
    )
);

#scatter plot to explore correlation
plt.scatter(df["area_m2"], df["price_usd"])
plt.xlabel("Area")
plt.ylabel("Price")
plt.title("Price vs Area")

#calculating actual correlation
p_correlation = df["area_m2"].corr(df["price_usd"])
#check if all OK
print(p_correlation)

#going inside, selecting a state, above scatter plot and correlation can be applied on the selection to verify the hypothesis
df_morelos = df[df["state"]== "Morelos"]

#doing it all together
# Subset `df` to include only observations from `"Distrito Federal"`
df_mexico_city = df[df["state"]=="Distrito Federal"]

# Create a scatter plot price vs area
plt.scatter(df_mexico_city["area_m2"], df_mexico_city["price_usd"])
plt.xlabel("Area")
plt.ylabel("Price")
plt.title("Area vs Price");

p_correlation = df_mexico_city["area_m2"].corr(df_mexico_city["price_usd"])
print(p_correlation)