Python Pandas: Ma'lumotlarni tahlil qilish

Pandas — Python da ma'lumotlar tahlili uchun eng asosiy kutubxona.

O'rnatish va import

pip install pandas

import pandas as pd
import numpy as np

DataFrame yaratish

ma'lumotlar = {
    "ism": ["Sherali", "Aziza", "Bobur", "Nilufar"],
    "yosh": [22, 25, 30, 28],
    "shahar": ["Toshkent", "Samarqand", "Buxoro", "Toshkent"],
    "maosh": [5000000, 7000000, 9000000, 6500000]
}

df = pd.DataFrame(ma'lumotlar)
print(df)
print(df.shape)       # (4, 4)
print(df.dtypes)      # har ustun turi
print(df.describe())  # statistika

Ma'lumot tanlash

print(df["ism"])              # ustun
print(df[["ism", "maosh"]])   # bir necha ustun
print(df.iloc[0])             # birinchi qator
print(df.loc[df["yosh"] > 25]) # shart bo'yicha

Filtrlash

toshkentliklar = df[df["shahar"] == "Toshkent"]
yuqori_maosh = df[df["maosh"] > 6000000]
ikki_shart = df[(df["yosh"] > 24) & (df["maosh"] > 6000000)]

Guruhlash

shahar_boyicha = df.groupby("shahar")["maosh"].mean()
print(shahar_boyicha)

# Bir necha aggregatsiya
natija = df.groupby("shahar").agg({
    "maosh": ["mean", "max", "count"],
    "yosh": "mean"
})

Ustun qo'shish va o'zgartirish

df["maosh_ming"] = df["maosh"] / 1000
df["yosh_kategoriya"] = pd.cut(df["yosh"], bins=[0, 25, 30, 100],
                                labels=["yosh", "o'rta", "katta"])

Saqlash va o'qish

df.to_csv("ma'lumotlar.csv", index=False)
df2 = pd.read_csv("ma'lumotlar.csv")

df.to_excel("ma'lumotlar.xlsx", index=False)