दिन 26: Descriptive Statistics

import numpy as np
import pandas as pd
salary = pd.Series([6, 6.5, 7, 7, 7.5, 8, 8, 8, 6, 60, 60], name="lakh")
print("Mean  :", round(salary.mean(), 2))
print("Median:", salary.median())
print("Mode  :", salary.mode().tolist())
print("Mean without founders:", round(salary[salary < 50].mean(), 2))

import pandas as pd
a = pd.Series([30, 31, 29, 30, 32, 28, 30], name="Courier A (minutes)")
b = pd.Series([10, 55, 20, 45, 30, 15, 35], name="Courier B (minutes)")
for s in (a, b):
    print(f"{s.name}: mean={s.mean():.1f} range={s.max() - s.min()} var={s.var():.1f} sd={s.std():.1f}")

import numpy as np
x = np.array([4, 8, 6, 5, 7])
mean = x.mean()
dev = x - mean
print("deviations:", dev, "| squared:", dev ** 2)
print("sample variance (÷ n-1):", (dev ** 2).sum() / (len(x) - 1), "=", x.var(ddof=1))
print("sample SD:", round(np.sqrt((dev ** 2).sum() / (len(x) - 1)), 3), "=", round(x.std(ddof=1), 3))

import pandas as pd
t = pd.read_csv("telecom_churn.csv")
bill = t["monthly_charges"]
print(bill.quantile([0, 0.25, 0.5, 0.75, 1]).round(0).to_dict())
print("90th percentile:", round(bill.quantile(0.9)), "→ top 10% pay more than this")
print("IQR:", round(bill.quantile(0.75) - bill.quantile(0.25)))

import pandas as pd
import matplotlib.pyplot as plt
t = pd.read_csv("telecom_churn.csv")
b = t["monthly_charges"]
fig, ax = plt.subplots(figsize=(9, 3.6))
ax.hist(b, bins=40, color="#c7d2fe", edgecolor="white")
for q, c, l in [(0.25, "#0891b2", "Q1"), (0.5, "#16a34a", "Median"), (0.75, "#0891b2", "Q3")]:
    ax.axvline(b.quantile(q), color=c, lw=2); ax.text(b.quantile(q), ax.get_ylim()[1] * 0.92, " " + l, color=c)
ax.axvline(b.mean(), color="#dc2626", ls="--", lw=2); ax.text(b.mean(), ax.get_ylim()[1] * 0.8, " Mean", color="#dc2626")
ax.set_title("Monthly bills: quartiles split customers into four equal groups"); ax.set_xlabel("₹ per month")
plt.show()

import pandas as pd
h = pd.read_csv("house_prices.csv")
s = pd.read_csv("sales_data.csv")
for name, col in [("House price", h["price_lakh"]), ("Unit price", s["unit_price"]), ("Customer age", s["customer_age"])]:
    print(f"{name:13s} mean={col.mean():9.1f} median={col.median():8.1f} skew={col.skew():5.2f} CV={col.std() / col.mean() * 100:5.1f}%")

import pandas as pd
st = pd.read_csv("students_performance.csv")
for subj in ["maths", "english"]:
    st[subj + "_z"] = ((st[subj] - st[subj].mean()) / st[subj].std()).round(2)
riya = st.iloc[7]
print(f"Student {riya.student_id}: maths {riya.maths} (z={riya.maths_z}), english {riya.english} (z={riya.english_z})")
print("Relative to classmates, the better subject is", "maths" if riya.maths_z > riya.english_z else "english")
print("Students with |z| > 2.5 in maths:", (st["maths_z"].abs() > 2.5).sum())

import pandas as pd
s = pd.read_csv("sales_data.csv")
s["revenue"] = s["quantity"] * s["unit_price"] * (1 - s["discount"])
s["z"] = (s["revenue"] - s["revenue"].mean()) / s["revenue"].std()
print("Orders with z > 3 (check for fraud or bulk buyers):", (s["z"] > 3).sum())
print(s.nlargest(3, "z")[["order_id", "product", "quantity", "revenue", "z"]].round(2).to_string(index=False))

import pandas as pd
e = pd.read_csv("employees.csv")
d = pd.read_csv("departments.csv")
df = e.merge(d, on="dept_id", how="left").fillna({"dept_name": "Unassigned"})
rep = df.groupby("dept_name")["salary"].describe()[["count", "mean", "50%", "std", "min", "max"]]
rep["cv_%"] = (rep["std"] / rep["mean"] * 100).round(1)
print((rep / [1, 1000, 1000, 1000, 1000, 1000, 1]).round(1).rename(columns={"50%": "median"}))
print("(salaries in ₹ thousand)")