Cơ bản về Khoa học Khí hậu

# Climate Data Analysis
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats

# Load NASA GISS temperature data
url = "https://data.giss.nasa.gov/gistemp/tabledata_v4/GLB.Ts+dSST.csv"
df = pd.read_csv(url, skiprows=1)

# Clean and prepare data
df = df[df["Year"] >= 1880]  # Reliable data from 1880
df["AnnualMean"] = df[["Jan", "Feb", "Mar", "Apr", "May", "Jun", 
                     "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]].mean(axis=1)

# Calculate temperature anomalies (base: 1951-1980)
base_period = df[(df["Year"] >= 1951) & (df["Year"] <= 1980)]
baseline = base_period["AnnualMean"].mean()
df["Anomaly"] = df["AnnualMean"] - baseline

# Linear regression for trend
slope, intercept, r_value, p_value, std_err = stats.linregress(df["Year"], df["Anomaly"])
print(f"Warming rate: {slope:.3f}°C per decade")
print(f"R-squared: {r_value**2:.3f}")

# Plotting
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10))

# Temperature anomaly trend
ax1.plot(df["Year"], df["Anomaly"], alpha=0.7, color="blue", label="Annual")
ax1.plot(df["Year"], slope * df["Year"] + intercept, "r-", label=f"Trend: {slope:.3f}°C/decade")
ax1.axhline(y=0, color="black", linestyle="--", alpha=0.5)
ax1.set_ylabel("Temperature Anomaly (°C)")
ax1.set_title("Global Temperature Anomalies (1880-2023)")
ax1.legend()
ax1.grid(True, alpha=0.3)

# Recent decades comparison
recent_30yr = df[df["Year"] >= 1994]["Anomaly"].mean()
early_30yr = df[(df["Year"] >= 1880) & (df["Year"] <= 1909)]["Anomaly"].mean()
difference = recent_30yr - early_30yr

ax2.bar(["1880-1909", "1994-2023"], [early_30yr, recent_30yr], 
        color=["lightblue", "red"], alpha=0.7)
ax2.set_ylabel("Average Temperature Anomaly (°C)")
ax2.set_title(f"30-Year Average Comparison\nDifference: {difference:.2f}°C")
ax2.axhline(y=0, color="black", linestyle="--", alpha=0.5)

plt.tight_layout()
plt.show()

# Key statistics
print(f"\nKey Climate Statistics:")
print(f"Temperature increase since 1880: {df.iloc[-1]["Anomaly"] - df.iloc[0]["Anomaly"]:.2f}°C")
print(f"Warmest year on record: {df.loc[df["Anomaly"].idxmax(), "Year"]} ({df["Anomaly"].max():.2f}°C)")
print(f"Number of years above 1°C warming: {len(df[df["Anomaly"] > 1.0])}")