Python สำหรับ Data Analytics: Matplotlib, Seaborn และการสร้างภาพข้อมูลสำหรับการสัมภาษณ์งาน

# setup.sh
python -m venv venv
source venv/bin/activate
pip install matplotlib==3.10.8 seaborn==0.13.2 pandas numpy

# verify_install.py
import matplotlib
import seaborn as sns
import pandas as pd

print(f"Matplotlib: {matplotlib.__version__}")
print(f"Seaborn: {sns.__version__}")
print(f"Pandas: {pd.__version__}")

# bar_chart_oo.py
import matplotlib.pyplot as plt
import numpy as np

# Sample quarterly revenue data
quarters = ["Q1", "Q2", "Q3", "Q4"]
revenue = [42_000, 58_000, 51_000, 67_000]

# Create figure and axes explicitly
fig, ax = plt.subplots(figsize=(8, 5))

# Draw bars with a specific color
ax.bar(quarters, revenue, color="#2563eb", width=0.5)

# Label axes clearly — interviewers check for this
ax.set_xlabel("Quarter")
ax.set_ylabel("Revenue (USD)")
ax.set_title("Quarterly Revenue — 2025")

# Format y-axis with dollar amounts
ax.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f"${x:,.0f}"))

# Remove top and right spines for a cleaner look
ax.spines[["top", "right"]].set_visible(False)

plt.tight_layout()
plt.savefig("quarterly_revenue.png", dpi=150)
plt.show()

# subplots_comparison.py
import matplotlib.pyplot as plt
import numpy as np

months = ["Jan", "Feb", "Mar", "Apr", "May", "Jun"]
users = [1200, 1350, 1500, 1420, 1680, 1820]
revenue = [24_000, 27_000, 30_000, 28_400, 33_600, 36_400]

# Two side-by-side plots sharing the x-axis
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 5), sharey=False)

# Left panel: user growth as a line chart
ax1.plot(months, users, marker="o", color="#2563eb", linewidth=2)
ax1.set_title("Monthly Active Users")
ax1.set_ylabel("Users")
ax1.spines[["top", "right"]].set_visible(False)

# Right panel: revenue as a bar chart
ax2.bar(months, revenue, color="#16a34a", width=0.5)
ax2.set_title("Monthly Revenue")
ax2.set_ylabel("Revenue (USD)")
ax2.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f"${x:,.0f}"))
ax2.spines[["top", "right"]].set_visible(False)

fig.suptitle("Product Metrics — H1 2025", fontsize=14, fontweight="bold")
plt.tight_layout()
plt.savefig("product_metrics.png", dpi=150)
plt.show()

# distribution_analysis.py
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# Simulate salary data for two departments
np.random.seed(42)
data = pd.DataFrame({
    "salary": np.concatenate([
        np.random.normal(75_000, 12_000, 200),  # Engineering
        np.random.normal(65_000, 10_000, 150),  # Marketing
    ]),
    "department": ["Engineering"] * 200 + ["Marketing"] * 150
})

# KDE plot comparing salary distributions
fig, ax = plt.subplots(figsize=(10, 5))
sns.kdeplot(
    data=data,
    x="salary",
    hue="department",        # Automatically splits by category
    fill=True,               # Shaded area under the curve
    alpha=0.4,
    palette=["#2563eb", "#dc2626"],
    ax=ax                    # Attach to our explicit axes
)

ax.set_title("Salary Distribution by Department")
ax.set_xlabel("Annual Salary (USD)")
ax.xaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f"${x:,.0f}"))
ax.spines[["top", "right"]].set_visible(False)

plt.tight_layout()
plt.savefig("salary_distribution.png", dpi=150)
plt.show()

# correlation_heatmap.py
import seaborn as sns
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

# Simulate e-commerce metrics
np.random.seed(42)
n = 500
page_views = np.random.poisson(15, n)
time_on_site = page_views * 2.5 + np.random.normal(0, 5, n)
cart_adds = np.random.binomial(page_views, 0.3)
purchases = np.random.binomial(cart_adds, 0.4)

df = pd.DataFrame({
    "page_views": page_views,
    "time_on_site": time_on_site,
    "cart_adds": cart_adds,
    "purchases": purchases
})

# Compute Pearson correlation
corr_matrix = df.corr()

fig, ax = plt.subplots(figsize=(8, 6))
sns.heatmap(
    corr_matrix,
    annot=True,              # Show correlation values in cells
    fmt=".2f",               # Two decimal places
    cmap="RdBu_r",           # Diverging colormap centered on 0
    vmin=-1, vmax=1,         # Fixed scale for consistency
    square=True,             # Square cells
    linewidths=0.5,
    ax=ax
)

ax.set_title("E-commerce Metrics Correlation")
plt.tight_layout()
plt.savefig("correlation_heatmap.png", dpi=150)
plt.show()

# professional_styling.py
import matplotlib.pyplot as plt
import seaborn as sns

# Apply Seaborn's built-in theme
sns.set_theme(
    style="whitegrid",       # Clean background with grid lines
    palette="muted",         # Professional color palette
    font_scale=1.1           # Slightly larger text
)

# Global Matplotlib overrides
plt.rcParams.update({
    "figure.facecolor": "white",
    "axes.facecolor": "white",
    "font.family": "sans-serif",
    "axes.titlesize": 14,
    "axes.labelsize": 12,
})

# interview_exercise.py
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np

sns.set_theme(style="whitegrid", palette="muted", font_scale=1.05)

# Simulate 12 months of product data
np.random.seed(42)
months = pd.date_range("2025-01", periods=12, freq="MS")
df = pd.DataFrame({
    "month": months,
    "revenue": np.cumsum(np.random.normal(5000, 2000, 12)) + 50_000,
    "customers": np.cumsum(np.random.poisson(50, 12)) + 500,
    "churn_rate": np.clip(np.random.normal(0.05, 0.015, 12), 0.01, 0.12)
})

fig, axes = plt.subplots(1, 3, figsize=(18, 5))

# Panel 1: Revenue trend
axes[0].plot(df["month"], df["revenue"], marker="o", color="#2563eb")
axes[0].set_title("Revenue Trend")
axes[0].set_ylabel("Revenue (USD)")
axes[0].yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f"${x:,.0f}"))
axes[0].tick_params(axis="x", rotation=45)
axes[0].spines[["top", "right"]].set_visible(False)

# Panel 2: Customer growth
axes[1].bar(df["month"], df["customers"], color="#16a34a", width=20)
axes[1].set_title("Customer Growth")
axes[1].set_ylabel("Total Customers")
axes[1].tick_params(axis="x", rotation=45)
axes[1].spines[["top", "right"]].set_visible(False)

# Panel 3: Churn rate with threshold line
axes[2].plot(df["month"], df["churn_rate"], marker="s", color="#dc2626")
axes[2].axhline(y=0.05, color="gray", linestyle="--", label="Target: 5%")
axes[2].set_title("Monthly Churn Rate")
axes[2].set_ylabel("Churn Rate")
axes[2].yaxis.set_major_formatter(plt.FuncFormatter(lambda x, _: f"{x:.1%}"))
axes[2].tick_params(axis="x", rotation=45)
axes[2].spines[["top", "right"]].set_visible(False)
axes[2].legend()

fig.suptitle("Product Dashboard — FY 2025", fontsize=14, fontweight="bold")
plt.tight_layout()
plt.savefig("interview_dashboard.png", dpi=150)
plt.show()