الفهرسة والتصفية والأقنعة المنطقية

loc في مقابل iloc

import pandas as pd

df = pd.DataFrame({"a":[1,2,3],"b":[4,5,6]}, index=["x","y","z"])
print(df.loc["y"])       # row with label y
print(df.iloc[1])        # row at position 1 (same row)
print(df.loc["x":"y"])   # rows x to y inclusive

التصفية باستخدام قناع منطقي

import pandas as pd

df = pd.DataFrame({"name":["Alice","Bob","Carol"],"age":[30,17,25]})
adults = df[df["age"] >= 18]
print(adults)
# Alice 30
# Carol 25

الشروط المتعددة

import pandas as pd

df = pd.DataFrame({"city":["NY","LA","NY","LA"],"score":[80,90,70,85]})
result = df[(df["city"]=="NY") & (df["score"]>75)]
print(result)

الدالة query()

import pandas as pd

df = pd.DataFrame({"age":[30,17,25],"score":[90,80,70]})
result = df.query("age >= 18 and score > 75")
print(result)

التصفية باستخدام isin()

import pandas as pd

df = pd.DataFrame({"city":["NY","LA","Chicago","NY"],"val":[1,2,3,4]})
print(df[df["city"].isin(["NY","LA"])])
# rows with NY or LA

استخدام between() لتصفية النطاق

import pandas as pd

df = pd.DataFrame({"score":[55,70,85,95,40]})
print(df[df["score"].between(60, 90)])
# 70 and 85

استخدام loc للتعيين

import pandas as pd

df = pd.DataFrame({"val":[1,2,3,4]})
df.loc[df["val"] > 2, "val"] = 99
print(df)
# 0:1  1:2  2:99  3:99

استخدام at وiat للقيم المفردة

import pandas as pd

df = pd.DataFrame({"a":[10,20],"b":[30,40]})
print(df.at[0,"a"])    # 10  (by label)
print(df.iat[1,1])     # 40  (by position)

التحديد حسب نوع البيانات

import pandas as pd

df = pd.DataFrame({"x":[1,2],"name":["a","b"],"score":[1.5,2.5]})
nums = df.select_dtypes(include=["number"])
print(nums.columns.tolist())   # ['x', 'score']

إزالة التكرارات

import pandas as pd

df = pd.DataFrame({"name":["Alice","Bob","Alice"],"age":[30,25,30]})
print(df.drop_duplicates())
# keeps first Alice, removes second

nlargest وnsmallest

import pandas as pd

df = pd.DataFrame({"product":["A","B","C","D"],"sales":[500,300,800,200]})
print(df.nlargest(2,"sales"))
# C 800
# A 500

تحقق سريع

مراجعة