6.6K Star！比 Pandas 快很多的数据处理库

>>> df = pl.DataFrame(
...     {
...         "A": [1, 2, 3, 4, 5],
...         "fruits": ["banana", "banana", "apple", "apple", "banana"],
...         "B": [5, 4, 3, 2, 1],
...         "cars": ["beetle", "audi", "beetle", "beetle", "beetle"],
...     }
... )

# embarrassingly parallel execution
# very expressive query language
>>> (
...     df
...     .sort("fruits")
...     .select(
...         [
...             "fruits",
...             "cars",
...             pl.lit("fruits").alias("literal_string_fruits"),
...             pl.col("B").filter(pl.col("cars") == "beetle").sum(),
...             pl.col("A").filter(pl.col("B") > 2).sum().over("cars").alias("sum_A_by_cars"),     # groups by "cars"
...             pl.col("A").sum().over("fruits").alias("sum_A_by_fruits"),                         # groups by "fruits"
...             pl.col("A").reverse().over("fruits").alias("rev_A_by_fruits"),                     # groups by "fruits
...             pl.col("A").sort_by("B").over("fruits").alias("sort_A_by_B_by_fruits"),            # groups by "fruits"
...         ]
...     )
... )
shape: (5, 8)
┌──────────┬──────────┬──────────────┬─────┬─────────────┬─────────────┬─────────────┬─────────────┐
│ fruits   ┆ cars     ┆ literal_stri ┆ B   ┆ sum_A_by_ca ┆ sum_A_by_fr ┆ rev_A_by_fr ┆ sort_A_by_B │
│ ---      ┆ ---      ┆ ng_fruits    ┆ --- ┆ rs          ┆ uits        ┆ uits        ┆ _by_fruits  │
│ str      ┆ str      ┆ ---          ┆ i64 ┆ ---         ┆ ---         ┆ ---         ┆ ---         │
│          ┆          ┆ str          ┆     ┆ i64         ┆ i64         ┆ i64         ┆ i64         │
╞══════════╪══════════╪══════════════╪═════╪═════════════╪═════════════╪═════════════╪═════════════╡
│ "apple"  ┆ "beetle" ┆ "fruits"     ┆ 11  ┆ 4           ┆ 7           ┆ 4           ┆ 4           │
├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ "apple"  ┆ "beetle" ┆ "fruits"     ┆ 11  ┆ 4           ┆ 7           ┆ 3           ┆ 3           │
├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ "banana" ┆ "beetle" ┆ "fruits"     ┆ 11  ┆ 4           ┆ 8           ┆ 5           ┆ 5           │
├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ "banana" ┆ "audi"   ┆ "fruits"     ┆ 11  ┆ 2           ┆ 8           ┆ 2           ┆ 2           │
├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌┤
│ "banana" ┆ "beetle" ┆ "fruits"     ┆ 11  ┆ 4           ┆ 8           ┆ 1           ┆ 1           │
└──────────┴──────────┴──────────────┴─────┴─────────────┴─────────────┴─────────────┴─────────────┘

import pandas as pd
import polars as pl
import timeit

# 读取时间对比
start_df = timeit.default_timer()
df = pd.read_csv("/Users/lenskit/Desktop/aa.csv")
df = df.sort_values("company_name", ascending=False).head()
stop_df = timeit.default_timer()
print('time: ', stop_df - start_df)

start_pl = timeit.default_timer()
data = pl.read_csv("/Users/lenskit/Desktop/aa.csv")
data.sort(by="company_name", reverse=True).head()
stop_pl = timeit.default_timer()
print('time1: ', stop_pl - start_pl)

# 纵向拼接时间对比
start_df1 = timeit.default_timer()
df_1 = pd.read_csv('/Users/lenskit/Desktop/aa.csv')
df_2 = pd.read_csv('/Users/lenskit/Desktop/bb.csv')
df_1.append(df_2, ignore_index=True)
stop_df1 = timeit.default_timer()
print('time2: ', stop_df1 - start_df1)

start_pl1 = timeit.default_timer()
pl_1 = pl.read_csv('/Users/lenskit/Desktop/aa.csv')
pl_2 = pl.read_csv('/Users/lenskit/Desktop/bb.csv')
pl_1.vstack(pl_2)
stop_pl1 = timeit.default_timer()
print('time3: ', stop_pl1 - start_pl1)


time:  5.088931238
time1:  0.8967700230000002
time2:  4.707102063
time3:  0.639797883

$ pip3 install -U polars[pyarrow]

polars = { git = "https://github.com/pola-rs/polars", rev = "<optional git tag>" }