import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

NAVY="#0a1230"; INK="#1a2138"; INK_SOFT="#4a5578"
CYAN="#0891b2"; PURPLE="#7c3aed"; AMBER="#d97706"; GREEN="#059669"; PINK="#db2777"
GRID="#e6e9f2"
plt.rcParams.update({
    "figure.facecolor":"white","axes.facecolor":"white","figure.dpi":110,
    "font.size":11,"axes.edgecolor":GRID,"axes.linewidth":1.2,
    "axes.grid":True,"grid.color":GRID,"axes.axisbelow":True,
    "axes.spines.top":False,"axes.spines.right":False,
    "axes.titlesize":14,"axes.titleweight":"bold","axes.titlecolor":INK,
    "axes.labelcolor":INK_SOFT,"xtick.color":INK_SOFT,"ytick.color":INK_SOFT,"legend.frameon":False,
})
print("✅ Ready.")

✅ Ready.

days = pd.Series([12, 15, 12, 18, 20, 12, 16, 15, 14, 12])

mean   = days.mean()
median = days.median()
mode   = days.mode().iloc[0]

print(f"Sorted data : {sorted(days)}")
print(f"Mean   : {mean:.1f}   (sum {days.sum()} / {len(days)} days)")
print(f"Median : {median:.1f}   (middle of the sorted values)")
print(f"Mode   : {mode}   (12 appears most often — 4 times)")

Sorted data : [12, 12, 12, 12, 14, 15, 15, 16, 18, 20]
Mean   : 14.6   (sum 146 / 10 days)
Median : 14.5   (middle of the sorted values)
Mode   : 12   (12 appears most often — 4 times)

# Visualize: how often each count occurs, with the three measures marked
counts = days.value_counts().sort_index()
fig, ax = plt.subplots(figsize=(9,4.3))
ax.bar(counts.index, counts.values, color=AMBER, alpha=0.85, edgecolor="white", width=0.7)
for v, lab, c in [(mean,"Mean","%s"%PURPLE),(median,"Median","%s"%CYAN),(mode,"Mode","%s"%GREEN)]:
    ax.axvline(v, color=c, ls="--", lw=2.4)
    ax.text(v, ax.get_ylim()[1]*0.95, f" {lab}", color=c, fontweight="bold", va="top")
ax.set_title("Challenge 1 — Customer counts", loc="left")
ax.set_xlabel("Daily customer count"); ax.set_ylabel("Number of days")
ax.set_yticks(range(0,5))
plt.tight_layout(); plt.show()

rng_val = days.max() - days.min()        # range = max - min
std_pop = days.std(ddof=0)               # population standard deviation

print(f"Max = {days.max()},  Min = {days.min()}")
print(f"Range              : {rng_val}")
print(f"Standard deviation : {std_pop:.2f}")
print()
print("Interpretation: most days fall within about", f"{std_pop:.1f}", "of the mean (14.4),")
print("so a typical day sees roughly 12-17 customers — fairly tightly clustered.")

Max = 20,  Min = 12
Range              : 8
Standard deviation : 2.65

Interpretation: most days fall within about 2.7 of the mean (14.4),
so a typical day sees roughly 12-17 customers — fairly tightly clustered.

# Show each day's distance from the mean (what standard deviation summarizes)
fig, ax = plt.subplots(figsize=(9,4.3))
idx = np.arange(1, len(days)+1)
ax.bar(idx, days.values - mean, color=[GREEN if v>=mean else PINK for v in days],
       alpha=0.85, edgecolor="white")
ax.axhline(0, color=NAVY, lw=1.5)
ax.set_title("Challenge 2 — Each day's deviation from the mean", loc="left")
ax.set_xlabel("Day"); ax.set_ylabel("Customers above / below mean")
ax.set_xticks(idx)
plt.tight_layout(); plt.show()

pets   = ["Dog", "Cat", "Fish", "Bird"]
votes  = [14, 9, 5, 3]
colors = [CYAN, PURPLE, AMBER, GREEN]

fig, ax = plt.subplots(figsize=(8,4.6))
bars = ax.bar(pets, votes, color=colors, alpha=0.9, edgecolor="white", width=0.65)

# Label each bar with its value
for b, v in zip(bars, votes):
    ax.text(b.get_x()+b.get_width()/2, v+0.3, str(v), ha="center", fontweight="bold", color=INK)

ax.set_title("Challenge 3 — Favorite Pet (class vote)", loc="left")
ax.set_xlabel("Pet"); ax.set_ylabel("Number of votes")
ax.set_ylim(0, 16)
plt.tight_layout(); plt.show()

print("Note: bars have GAPS because the data is categorical (a bar chart).")
print("If the x-axis were numeric ranges, touching bars would make it a histogram.")

Note: bars have GAPS because the data is categorical (a bar chart).
If the x-axis were numeric ranges, touching bars would make it a histogram.

⚙️ Setup¶