Matplotlib 히스토그램: Python에서 plt.hist()의 완전 가이드

import matplotlib.pyplot as plt
import numpy as np
 
# Generate 1000 normally distributed values
np.random.seed(42)
data = np.random.normal(loc=50, scale=15, size=1000)
 
plt.hist(data)
plt.title('Basic Histogram')
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.show()

plt.hist(x, bins=None, range=None, density=False, weights=None,
         cumulative=False, bottom=None, histtype='bar', align='mid',
         orientation='vertical', rwidth=None, log=False, color=None,
         label=None, stacked=False, edgecolor=None, alpha=None)

fig, axes = plt.subplots(1, 3, figsize=(14, 4))
 
axes[0].hist(data, bins=5, edgecolor='black')
axes[0].set_title('5 Bins')
 
axes[1].hist(data, bins=30, edgecolor='black')
axes[1].set_title('30 Bins')
 
axes[2].hist(data, bins=100, edgecolor='black')
axes[2].set_title('100 Bins')
 
plt.tight_layout()
plt.show()

custom_edges = [0, 20, 35, 50, 65, 80, 100]
plt.hist(data, bins=custom_edges, edgecolor='black', color='steelblue')
plt.title('Histogram with Custom Bin Edges')
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.show()

fig, axes = plt.subplots(1, 3, figsize=(14, 4))
 
for ax, method in zip(axes, ['sturges', 'scott', 'fd']):
    ax.hist(data, bins=method, edgecolor='black', color='#4C72B0')
    ax.set_title(f'bins="{method}"')
 
plt.tight_layout()
plt.show()

fig, axes = plt.subplots(1, 2, figsize=(12, 4))
 
axes[0].hist(data, bins=30, edgecolor='black', color='#55A868')
axes[0].set_title('Frequency (default)')
axes[0].set_ylabel('Count')
 
axes[1].hist(data, bins=30, edgecolor='black', color='#C44E52', density=True)
axes[1].set_title('Density (density=True)')
axes[1].set_ylabel('Probability Density')
 
plt.tight_layout()
plt.show()

from scipy import stats
 
plt.hist(data, bins=30, density=True, edgecolor='black', color='#55A868', alpha=0.7)
 
# Overlay the theoretical normal curve
x_range = np.linspace(data.min(), data.max(), 200)
plt.plot(x_range, stats.norm.pdf(x_range, loc=50, scale=15), 'r-', linewidth=2, label='Normal PDF')
plt.legend()
plt.title('Density Histogram with Normal Curve Overlay')
plt.show()

plt.hist(data, bins=30, color='#4C72B0', edgecolor='white', alpha=0.85)
plt.title('Styled Histogram')
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.show()

fig, axes = plt.subplots(2, 2, figsize=(10, 8))
types = ['bar', 'barstacked', 'step', 'stepfilled']
 
for ax, ht in zip(axes.flat, types):
    ax.hist(data, bins=30, histtype=ht, edgecolor='black', color='#4C72B0')
    ax.set_title(f'histtype="{ht}"')
 
plt.tight_layout()
plt.show()

np.random.seed(42)
group_a = np.random.normal(loc=50, scale=10, size=800)
group_b = np.random.normal(loc=65, scale=12, size=800)
 
plt.hist(group_a, bins=30, alpha=0.6, color='#4C72B0', edgecolor='black', label='Group A')
plt.hist(group_b, bins=30, alpha=0.6, color='#C44E52', edgecolor='black', label='Group B')
plt.legend()
plt.title('Overlapping Histograms')
plt.xlabel('Score')
plt.ylabel('Frequency')
plt.show()

plt.hist([group_a, group_b], bins=20, color=['#4C72B0', '#C44E52'],
         edgecolor='black', label=['Group A', 'Group B'])
plt.legend()
plt.title('Side-by-Side Histograms')
plt.xlabel('Score')
plt.ylabel('Frequency')
plt.show()

np.random.seed(42)
freshmen = np.random.normal(loc=68, scale=8, size=500)
sophomores = np.random.normal(loc=72, scale=7, size=400)
juniors = np.random.normal(loc=75, scale=6, size=300)
 
plt.hist([freshmen, sophomores, juniors], bins=25, stacked=True,
         color=['#4C72B0', '#55A868', '#C44E52'], edgecolor='black',
         label=['Freshmen', 'Sophomores', 'Juniors'])
plt.legend()
plt.title('Stacked Histogram: Exam Scores by Class Year')
plt.xlabel('Score')
plt.ylabel('Frequency')
plt.show()

fig, axes = plt.subplots(1, 2, figsize=(12, 4))
 
axes[0].hist(data, bins=30, cumulative=True, edgecolor='black', color='#DD8452')
axes[0].set_title('Cumulative Histogram (Count)')
axes[0].set_ylabel('Cumulative Count')
 
axes[1].hist(data, bins=30, cumulative=True, density=True, edgecolor='black', color='#8172B3')
axes[1].set_title('Cumulative Histogram (Density)')
axes[1].set_ylabel('Cumulative Probability')
 
plt.tight_layout()
plt.show()

plt.hist(data, bins=30, orientation='horizontal', color='#64B5CD', edgecolor='black')
plt.title('Horizontal Histogram')
plt.xlabel('Frequency')
plt.ylabel('Value')
plt.show()

n, bin_edges, patches = plt.hist(data, bins=20, edgecolor='black', color='#4C72B0')
plt.show()
 
print(f"Bin counts (n): shape = {n.shape}, first 5 = {n[:5]}")
print(f"Bin edges: shape = {bin_edges.shape}, first 5 = {bin_edges[:5]}")
print(f"Patches: {len(patches)} Rectangle objects")

n, bin_edges, patches = plt.hist(data, bins=30, edgecolor='black')
 
# Color bars based on height
for count, patch in zip(n, patches):
    if count > 50:
        patch.set_facecolor('#C44E52')
    else:
        patch.set_facecolor('#4C72B0')
 
plt.title('Conditional Bar Coloring')
plt.show()

pip install pygwalker

import pandas as pd
import pygwalker as pyg
 
# Load your dataset into a DataFrame
df = pd.DataFrame({
    'score': np.random.normal(70, 12, 2000),
    'group': np.random.choice(['A', 'B', 'C'], 2000)
})
 
# Launch the interactive UI
walker = pyg.walk(df)