Vizualizatsiya: ma'lumotni ko'rish

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

sns.set_theme(style="whitegrid", font_scale=1.05)
df = pd.read_csv(DATA / "uy_ijara.csv")

# MATPLOTLIB usuli — qo'lda guruhlash, qo'lda joylash
rasm, axes = plt.subplots(1, 2, figsize=(14, 4.8))

g = df.groupby("tuman").narx_usd.mean().sort_values()
axes[0].barh(range(len(g)), g.values, color="#5f6368")
axes[0].set_yticks(range(len(g)))
axes[0].set_yticklabels(g.index)
axes[0].set_xlabel("O'rtacha narx (USD)")
axes[0].set_title("matplotlib — 6 qator kod", fontweight="bold")

# SEABORN usuli — bitta qator
sns.barplot(data=df, y="tuman", x="narx_usd", estimator="mean",
            errorbar=None, ax=axes[1], order=g.index, color="#1a73e8")
axes[1].set_xlabel("O'rtacha narx (USD)")
axes[1].set_title("seaborn — 1 qator kod", fontweight="bold")

fig("matplotlib_vs_seaborn.png", caption="Bir xil natija. Chapda qo'lda guruhlash, o'ngda seaborn o'zi guruhlaydi.")

rasm, axes = plt.subplots(1, 3, figsize=(15, 4.2))

sns.histplot(data=df, x="narx_usd", bins=35, kde=True, ax=axes[0], color="#1a73e8")
axes[0].set_title("histplot — shakl")

sns.boxplot(data=df, x="narx_usd", ax=axes[1], color="#43a047")
axes[1].set_title("boxplot — median, chorak, chetlar")

sns.violinplot(data=df, x="narx_usd", ax=axes[2], color="#8e24aa")
axes[2].set_title("violinplot — shakl + chorak")

fig("taqsimot.png", caption="Bir xil ustun, uch xil ko'rinish. histplot shaklni, boxplot chetki qiymatlarni ko'rsatadi.")

print(df.narx_usd.describe().round(1).to_string())
print()
q1, q3 = df.narx_usd.quantile([0.25, 0.75])
iqr = q3 - q1
chet = df[(df.narx_usd < q1 - 1.5 * iqr) | (df.narx_usd > q3 + 1.5 * iqr)]
print(f"Chorak oralig'i (IQR): {iqr:.0f}")
print(f"Boxplot 'chet' deb ko'rsatadigan qatorlar: {len(chet)} ta ({len(chet)/len(df):.1%})")

rasm, axes = plt.subplots(1, 2, figsize=(14, 4.8))

sns.scatterplot(data=df, x="maydon_m2", y="narx_usd", hue="mebel",
                alpha=.55, ax=axes[0], palette=["#c5221f", "#137333"])
axes[0].set_title("Maydon va narx (rang = mebel)")

sns.scatterplot(data=df, x="metro_km", y="narx_usd", alpha=.45, ax=axes[1], color="#1a73e8")
sns.regplot(data=df, x="metro_km", y="narx_usd", scatter=False, ax=axes[1], color="#c5221f")
axes[1].set_title("Metroga masofa va narx (qizil chiziq = trend)")

fig("boglanish.png", caption="Chapda: maydon oshsa narx oshadi. O'ngda: metro uzoqlashsa narx tushadi, lekin tarqalish katta.")

son_ustunlar = ["xonalar", "maydon_m2", "qavat", "qavatlar_soni", "metro_km", "mebel", "narx_usd"]
korr = df[son_ustunlar].corr()
print("narx_usd bilan korrelyatsiya:")
print(korr["narx_usd"].drop("narx_usd").sort_values(ascending=False).round(3).to_string())

rasm, ax = plt.subplots(figsize=(8.5, 6.5))
sns.heatmap(korr, annot=True, fmt=".2f", cmap="RdBu_r", center=0,
            square=True, linewidths=.5, ax=ax, cbar_kws={"shrink": .8})
ax.set_title("Korrelyatsiya matritsasi", fontweight="bold")
fig("heatmap.png", caption="Qizil = ijobiy bog'liqlik, ko'k = salbiy. xonalar va maydon_m2 orasidagi 0.94 ga diqqat qiling.")

rasm, axes = plt.subplots(1, 3, figsize=(16, 4.5))

sns.countplot(data=df, y="tuman", ax=axes[0], color="#5f6368",
              order=df.tuman.value_counts().index)
axes[0].set_title("countplot — nechta e'lon")

sns.boxplot(data=df, x="xonalar", y="narx_usd", ax=axes[1], hue="xonalar",
            legend=False, palette="Blues")
axes[1].set_title("boxplot — xona soni va narx")

sns.barplot(data=df, x="xonalar", y="ijaraga_berildi_30k", ax=axes[2],
            errorbar=("ci", 95), color="#137333")
axes[2].set_ylabel("Tez ketish ulushi")
axes[2].set_title("barplot — ishonch oralig'i bilan")

fig("kategoriya.png", caption="countplot sonni, boxplot taqsimotni, barplot o'rtachani (ishonch oralig'i bilan) ko'rsatadi.")

print("Xona soni bo'yicha tez ketish ulushi:")
g = df.groupby("xonalar").agg(soni=("ijaraga_berildi_30k", "size"),
                              tez_ketish=("ijaraga_berildi_30k", "mean"))
g["tez_ketish"] = g.tez_ketish.round(3)
print(g.to_string())
print()
print("DIQQAT: 5 xonali kvartiralar soni kam — ularning ulushiga ishonch past.")

qism = df[df.xonalar.isin([1, 2, 3])]
g = sns.relplot(data=qism, x="maydon_m2", y="narx_usd",
                hue="mebel", col="xonalar", kind="scatter",
                height=3.8, aspect=1.05, alpha=.6,
                palette=["#c5221f", "#137333"])
g.figure.suptitle("Maydon va narx: xona soni bo'yicha ajratilgan", y=1.04, fontweight="bold")
fig("relplot.png", caption="col='xonalar' uchta panel yaratdi. hue='mebel' rang bilan to'rtinchi o'lchovni qo'shdi.")

show(pd.DataFrame([
    {"Savol": "Bitta son ustuni qanday taqsimlangan?", "Grafik": "histplot", "Qo'shimcha": "kde=True shaklni silliqlaydi"},
    {"Savol": "Chetki qiymatlar bormi?", "Grafik": "boxplot", "Qo'shimcha": "Nuqtalar = IQR dan tashqarida"},
    {"Savol": "Ikki son orasida aloqa bormi?", "Grafik": "scatterplot", "Qo'shimcha": "regplot trend chizig'ini qo'shadi"},
    {"Savol": "Hamma son ustunlari o'zaro?", "Grafik": "heatmap(corr)", "Qo'shimcha": "yoki pairplot (sekin)"},
    {"Savol": "Kategoriyada nechta qator?", "Grafik": "countplot", "Qo'shimcha": "order= bilan saralang"},
    {"Savol": "Kategoriya bo'yicha o'rtacha?", "Grafik": "barplot", "Qo'shimcha": "errorbar ni O'CHIRMANG"},
    {"Savol": "Kategoriya bo'yicha taqsimot?", "Grafik": "boxplot / violinplot", "Qo'shimcha": "barplot dan ko'proq ma'lumot beradi"},
    {"Savol": "Vaqt bo'yicha o'zgarish?", "Grafik": "lineplot", "Qo'shimcha": "x o'qi sana bo'lishi kerak"},
    {"Savol": "Uch-to'rt o'lchov birga?", "Grafik": "relplot / catplot", "Qo'shimcha": "hue, col, row"},
]))

rasm, axes = plt.subplots(1, 4, figsize=(17, 4))
for ax, u in zip(axes, ["maydon_m2", "metro_km", "narx_usd", "qavat"]):
    sns.boxplot(data=df, x="ijaraga_berildi_30k", y=u, ax=ax,
                hue="ijaraga_berildi_30k", legend=False, palette=["#c5221f", "#137333"])
    ax.set_xlabel("0 = sekin ketdi   1 = tez ketdi")
    ax.set_title(u)
fig("target_ajratish.png", caption="Qutilar bir-biridan qanchalik ajralgan bo'lsa, o'sha xususiyat shunchalik foydali.")

print("Har bir xususiyat target ni qanchalik ajratadi:")
qatorlar = []
for u in ["maydon_m2", "metro_km", "narx_usd", "qavat", "xonalar", "mebel"]:
    a = df[df.ijaraga_berildi_30k == 0][u].mean()
    b = df[df.ijaraga_berildi_30k == 1][u].mean()
    birlashgan_std = df[u].std()
    qatorlar.append({"Ustun": u, "Sekin o'rtacha": round(a, 2), "Tez o'rtacha": round(b, 2),
                     "Ajratish kuchi": round(abs(b - a) / birlashgan_std, 3)})
show(pd.DataFrame(qatorlar).sort_values("Ajratish kuchi", ascending=False))

sns.set_theme(style="whitegrid", font_scale=1.1)
rasm, ax = plt.subplots(figsize=(10, 5))
g = df.groupby("tuman").agg(ortacha=("narx_usd", "mean"),
                            soni=("narx_usd", "size")).sort_values("ortacha")
sns.barplot(x=g.ortacha, y=g.index, ax=ax, color="#1a73e8")
for i, (v, n) in enumerate(zip(g.ortacha, g.soni)):
    ax.text(v + 8, i, f"{v:.0f} USD  (n={n})", va="center", fontsize=9.5, color="#333")
ax.set_xlabel("O'rtacha ijara narxi, USD/oy")
ax.set_ylabel("")
ax.set_title("Toshkent tumanlari bo'yicha o'rtacha ijara narxi", fontweight="bold", pad=14)
ax.set_xlim(0, g.ortacha.max() * 1.28)
sns.despine(left=True, bottom=True)
fig("hisobot.png", caption="Hisobotga tayyor grafik: qiymat yozilgan, guruh hajmi (n) ko'rsatilgan, chiziqlar olib tashlangan.")

show(pd.DataFrame([
    {"Qoida": "Avval ko'r, keyin model qur", "Nega": "Grafik bir sekundda jadvaldan ko'proq aytadi"},
    {"Qoida": "seaborn — DataFrame tilida", "Nega": "Ustun nomini berasiz, u guruhlaydi va chizadi"},
    {"Qoida": "Grafikni RAQAM bilan tekshir", "Nega": "Ko'z aldaydi; describe() va corr() tasdiqlaydi"},
    {"Qoida": "Guruh hajmini ko'rsat", "Nega": "3 qatorli guruh o'rtachasi ma'nosiz"},
    {"Qoida": "errorbar ni o'chirma", "Nega": "Ustma-ust tushgan oraliq = farq ishonchli emas"},
    {"Qoida": "Chetki qiymatni o'qib tashla", "Nega": "Hammasi xato emas — ba'zilari haqiqat"},
    {"Qoida": "Target bo'yicha ajratib ko'r", "Nega": "Qaysi xususiyat foydali ekanini oldindan ko'rsatadi"},
]))