A histogram is a bar chart that divides numerical data into equal-width intervals, or bins, and counts the values in each one. It reveals which ranges are common and shows the overall shape of the data. section 2.20
Tornado widths
Plotting tornado-path widths with 60 bins reveals heavy right skew: most tornadoes are relatively narrow, while a long tail contains wider outliers. Increasing the bin count adds detail; using too few bins oversmooths the shape, while using too many can make it noisy. Compare the histogram with the mean, median, and percentiles before interpreting it. section 2.20
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
df = pd.read_csv("https://raw.githubusercontent.com/thomasnield/"
"training-data-repository/refs/heads/main/TORNADO_TRX.csv")
tor_width = df['TOR_WIDTH']
print("MEAN: ", np.mean(tor_width)) # MEAN: 215.18971962616823
print("MEDIAN: ", np.median(tor_width)) # MEDIAN: 100.0
print("ST DEV: ", np.std(tor_width, ddof=1)) # ST DEV: 315.83093225491433
print("25th PCT: ", np.percentile(tor_width, 25)) # 25th PCT: 50.0
print("75th PCT: ", np.percentile(tor_width, 75)) # 75th PCT: 250.0
print(df['TOR_F_SCALE'].value_counts())
# TOR_F_SCALE
# EF1 1250
# EF0 1047
# EFU 497
# EF2 323
# EF3 86
# EF4 7
# Create a histogram using matplotlib
plt.hist(tor_width, bins=60, edgecolor='black') # Adjust bins as needed
plt.title('Histogram of Tornado Width')
plt.xlabel('Width')
plt.ylabel('Frequency')
plt.grid(True, alpha=0.3)
plt.show()
Run the Python example to calculate summary statistics and create a Matplotlib histogram of tornado widths. section 2.20
