# Let us start by suppressing warnings to keep output clean
import warnings
warnings.filterwarnings("ignore")
 
 

# Print a welcome message
print("Hello, world! Climate and Python together.")

# This is a comment: Comments never run as code

# Data setup
import pandas as pd
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv"
climate_df = pd.read_csv(url)
print("Dataset shape:", climate_df.shape)
climate_df.head()

# Simple plot: temperature over time
import matplotlib.pyplot as plt
plt.figure(figsize=(10,4))
plt.plot(climate_df["Date"], climate_df["Temp"])
plt.xlabel("Date")
plt.ylabel("Daily Min Temperature")
plt.title("Daily Minimum Temperatures - Sydney")
plt.xticks([])
plt.show()

city = "Sydney"
average_temp = 17.5
days_measured = 365

print("City:", city)
print("Average temperature:", average_temp)
print("Days measured:", days_measured)

user_name = input("What is your name? ")
city_guess = input("What city do you think this weather data is from? ")
print("Hello,", user_name)
print("You guessed:", city_guess)

# Step 4: Lists for Sequences
temps_sample = [13, 17, 15, 14, 18]
print("Some sample temperatures:", temps_sample)

# Add a new temperature
temps_sample.append(20)
print("With another temp:", temps_sample)

# Step 5: Basic math and statistics
total = sum(temps_sample)
count = len(temps_sample)
average = total / count
print("Average temperature:", average)

# Select first 5 temperature values
five_days = climate_df["Temp"].iloc[:5]
print("First five day's temperatures:", list(five_days))

# Safe column access with get
safe_temp = climate_df.get("Temp", None)
safe_notfound = climate_df.get("Rainfall", None)
print("Safely found temperature?", safe_temp is not None)
print("Safely found Rainfall column?", safe_notfound is not None)

# Step 7: Filtering data by condition
hot_days = climate_df[climate_df["Temp"] > 20]
print("How many days above 20 degrees?", len(hot_days))
hot_days.head(3)

# Step 8: Sorting data
sorted_days = climate_df.sort_values("Temp", ascending=False)
print("Hottest recorded temperatures at the top:")
sorted_days.head()

# Step 9: Simple line plot for filtered data
plt.figure(figsize=(8,3))
plt.plot(hot_days["Date"], hot_days["Temp"], color="red")
plt.title("Hot Days Only")
plt.ylabel("Temperature")
plt.xlabel("Date")
plt.xticks([])
plt.show()

# Step 10: Grouping data - monthly average
climate_df["Date"] = pd.to_datetime(climate_df["Date"])
climate_df["Month"] = climate_df["Date"].dt.month
monthly_avg = climate_df.groupby("Month")["Temp"].mean()
print("Monthly average temperatures:", monthly_avg.values)

# Step 11: Quick bar chart - average temperature by month
plt.figure(figsize=(8,3))
plt.bar(monthly_avg.index, monthly_avg.values, color="cornflowerblue")
plt.xlabel("Month")
plt.ylabel("Average Temp")
plt.title("Average Temperature by Month")
plt.show()

# Step 12: Combine data - make a DataFrame from scratch
import numpy as np
cities = ["Sydney", "Melbourne", "Brisbane"]
jan_avg = [22, 20, 25]
jul_avg = [13, 10, 15]
multi_city = pd.DataFrame({"City": cities, "Jan": jan_avg, "Jul": jul_avg})
print(multi_city)

# Step 13: Quick scatter plot for city coordinates
lat = [-33.8688, -37.8136, -27.4698]
lon = [151.2093, 144.9631, 153.0251]
multi_city["Lat"] = lat
multi_city["Lon"] = lon
plt.figure(figsize=(6,6))
plt.scatter(multi_city["Lon"], multi_city["Lat"], color="lawngreen", s=200)
for i, row in multi_city.iterrows():
    plt.text(row["Lon"]+0.2, row["Lat"], row["City"], fontsize=12)
plt.xlabel("Longitude")
plt.ylabel("Latitude")
plt.title("Major Australian Cities - Location Map")
plt.show()

# Step 14: Challenge! What city is farthest north?
northern = multi_city.loc[multi_city["Lat"].idxmax()]
print("Farthest north city:", northern["City"])