Introduction to Data Visualization with Matplotlib

# Importing course packages; you can add more too!
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# Importing course datasets as DataFrames
climate_change = pd.read_csv('datasets/climate_change.csv', parse_dates=["date"], index_col="date")
medals = pd.read_csv('datasets/medals_by_country_2016.csv', index_col=0)
summer_2016 = pd.read_csv('datasets/summer2016.csv')
austin_weather = pd.read_csv("datasets/austin_weather.csv", index_col="DATE")
weather = pd.read_csv("datasets/seattle_weather.csv", index_col="DATE")

# Some pre-processing on the weather datasets, including adding a month column
seattle_weather = weather[weather["STATION"] == "USW00094290"].copy()  # Make a copy of the DataFrame
month = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"] 
seattle_weather.loc[:, "MONTH"] = month  # Use .loc to assign the values
austin_weather.loc[:, "MONTH"] = month  # Use .loc to assign the values

# seattle_weather["MONTH"] = month 
# austin_weather["MONTH"] = month

austin_weather.head() # Display the first five rows of this DataFrame

# Begin writing your own code here!
# Task 1: Plotting Seattle and Austin weather
fig, axes = plt.subplots(nrows=2, ncols=1, sharey=True, figsize=(10, 8))

# Plotting average temperature
axes[0].plot(seattle_weather["MONTH"], seattle_weather["MLY-TAVG-NORMAL"], color="blue", linestyle="-", label="Seattle")
axes[0].plot(austin_weather["MONTH"], austin_weather["MLY-TAVG-NORMAL"], color="red", linestyle="-", label="Austin")
axes[0].set_ylabel("Average Temperature (°C)")
axes[0].set_title("Monthly Average Temperature")
axes[0].legend()

# Plotting average precipitation
axes[1].plot(seattle_weather["MONTH"], seattle_weather["MLY-PRCP-NORMAL"], color="blue", linestyle="--", label="Seattle")
axes[1].plot(austin_weather["MONTH"], austin_weather["MLY-PRCP-NORMAL"], color="red", linestyle="--", label="Austin")
axes[1].set_xlabel("Months")
axes[1].set_ylabel("Average Precipitation (mm)")
axes[1].set_title("Monthly Average Precipitation")
axes[1].legend()

plt.tight_layout()
plt.show()

# Task 2: Plotting climate change data
fig, ax1 = plt.subplots(figsize=(10, 6))
ax2 = ax1.twinx()

# Filtering data for the 2000s
climate_change_2000s = climate_change[climate_change["date"].dt.year >= 2000]

# Plotting CO2 levels
ax1.plot(climate_change_2000s["date"], climate_change_2000s["co2"], color="blue", label="CO2")
ax1.set_ylabel("CO2 (ppm)")

# Plotting relative temperature
ax2.plot(climate_change_2000s["date"], climate_change_2000s["relative_temp"], color="red", label="Relative Temp")
ax2.set_ylabel("Relative Temperature (°C)")

# Annotating the first date when CO2 exceeded 400
first_date_exceed_400 = climate_change_2000s[climate_change_2000s["co2"] > 400]["date"].iloc[0]
ax1.annotate("CO2 > 400", xy=(first_date_exceed_400, climate_change_2000s["co2"].max()), xytext=(first_date_exceed_400, 410),
             arrowprops=dict(arrowstyle="->"), fontsize=12)

ax1.set_title("Climate Change")
ax1.set_xlabel("Year")
ax1.legend(loc="upper left")
ax2.legend(loc="upper right")

plt.show()

# Task 3: Scatter plot of Gold vs Silver medals
fig, ax = plt.subplots(figsize=(8, 6))
ax.scatter(medals["Gold"], medals["Silver"], c=medals.index, cmap="tab20")
ax.set_xlabel("Gold Medals")
ax.set_ylabel("Silver Medals")
ax.set_title("Gold vs Silver Medals")
for i, country in enumerate(medals.index):
    ax.annotate(country, (medals["Gold"][i], medals["Silver"][i]), fontsize=8)

plt.show()

# Task 4: Histograms of Age by sport
sports = summer_2016["Sport"].unique()
fig, axes = plt.subplots(nrows=len(sports), ncols=1, figsize=(8, 20), sharex=True)

for i, sport in enumerate(sports):
    axes[i].hist(summer_2016[summer_2016["Sport"] == sport]["Age"], bins=15, alpha=0.7)
    axes[i].set_title(sport)
    axes[i].set_ylabel("Frequency")

plt.xlabel("Age")
plt.tight_layout()
plt.show()