दिन 21: Matplotlib: Line, Bar, Scatter, Subplots

import matplotlib.pyplot as plt
months = ["Jan", "Feb", "Mar", "Apr", "May", "Jun"]
sales_2023 = [4.1, 3.8, 4.6, 4.9, 5.3, 5.0]
sales_2024 = [4.8, 4.4, 5.2, 5.9, 6.4, 6.1]
fig, ax = plt.subplots(figsize=(8, 4))
ax.plot(months, sales_2023, marker="o", color="#94a3b8", label="2023")
ax.plot(months, sales_2024, marker="o", color="#4f46e5", lw=2.5, label="2024")
ax.set_title("Monthly sales (₹ lakh): 2024 is ahead every month")
ax.set_xlabel("Month"); ax.set_ylabel("₹ lakh"); ax.legend()
ax.annotate("Best month", xy=(4, 6.4), xytext=(2.4, 6.15), arrowprops=dict(arrowstyle="->"))
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
s = pd.read_csv("sales_data.csv")
s["revenue"] = s["quantity"] * s["unit_price"] * (1 - s["discount"])
city = (s.groupby("city")["revenue"].sum() / 1e5).sort_values()
colors = ["#4f46e5" if v == city.max() else "#c7d2fe" for v in city]
fig, ax = plt.subplots(figsize=(8, 4.5))
bars = ax.barh(city.index, city.values, color=colors)
ax.bar_label(bars, fmt="%.1f", padding=3, fontsize=8)
ax.set_title("Mumbai leads revenue (₹ lakh, 2024)"); ax.set_xlabel("₹ lakh")
ax.spines[["top", "right"]].set_visible(False)
plt.show()

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
s = pd.read_csv("sales_data.csv")
pv = pd.crosstab(s["category"], s["customer_gender"])
x = np.arange(len(pv)); w = 0.38
fig, ax = plt.subplots(figsize=(9, 4))
ax.bar(x - w / 2, pv["Female"], w, label="Female", color="#ec4899")
ax.bar(x + w / 2, pv["Male"], w, label="Male", color="#3b82f6")
ax.set_xticks(x, pv.index, rotation=10); ax.set_ylabel("Orders"); ax.legend()
ax.set_title("Orders by category and gender")
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
h = pd.read_csv("house_prices.csv")
fig, ax = plt.subplots(1, 2, figsize=(11, 4))
for city, color in [("Bengaluru", "#4f46e5"), ("Lucknow", "#f59e0b")]:
    d = h[h["city"] == city]
    ax[0].scatter(d["area_sqft"], d["price_lakh"], s=14, alpha=0.6, color=color, label=city)
ax[0].set_xlabel("Area (sqft)"); ax[0].set_ylabel("₹ lakh"); ax[0].legend(); ax[0].set_title("Same area, different city price")
s = pd.read_csv("sales_data.csv")
ax[1].hist(s["customer_age"].dropna(), bins=20, color="#0891b2", edgecolor="white")
ax[1].axvline(s["customer_age"].median(), color="#dc2626", ls="--", label="median")
ax[1].set_title("Customer age distribution"); ax[1].set_xlabel("Age"); ax[1].legend()
plt.tight_layout(); plt.show()

import pandas as pd
import matplotlib.pyplot as plt
s = pd.read_csv("sales_data.csv", parse_dates=["order_date"])
s["revenue"] = s["quantity"] * s["unit_price"] * (1 - s["discount"])
fig, ax = plt.subplots(2, 2, figsize=(11, 7))
m = s.groupby(s["order_date"].dt.month)["revenue"].sum() / 1e5
ax[0, 0].plot(m.index, m.values, marker="o", color="#4f46e5"); ax[0, 0].set_title("Revenue by month (₹ lakh)")
c = s.groupby("category")["revenue"].sum().sort_values()
ax[0, 1].barh(c.index, c / 1e5, color="#0891b2"); ax[0, 1].set_title("Revenue by category")
p = s["payment_mode"].value_counts()
ax[1, 0].pie(p, labels=p.index, autopct="%1.0f%%", wedgeprops=dict(width=0.45)); ax[1, 0].set_title("Payment mode")
ax[1, 1].hist(s["rating"].dropna(), bins=[1.75, 2.25, 2.75, 3.25, 3.75, 4.25, 4.75, 5.25], color="#16a34a", edgecolor="white"); ax[1, 1].set_title("Ratings")
fig.suptitle("BazaarKart 2024 at a glance", fontsize=15, fontweight="bold")
plt.tight_layout(); plt.savefig("dashboard.png", dpi=150); plt.show()