十个Pandas的另类数据处理技巧

# raw data
 +----------+------------------------+
 |  class   |        filename        |
 +----------+------------------------+
 | Bathroom | Bathroom\bath_1.jpg    |
 | Bathroom | Bathroom\bath_100.jpg  |
 | Bathroom | Bathroom\bath_1003.jpg |
 | Bathroom | Bathroom\bath_1004.jpg |
 | Bathroom | Bathroom\bath_1005.jpg |
 +----------+------------------------+
 
 # target
 +------------------------+------------------------+----------------------------+
 |         anchor         |        positive        |          negative          |
 +------------------------+------------------------+----------------------------+
 | Bathroom\bath_1.jpg    | Bathroom\bath_100.jpg  | Dinning\din_540.jpg        |
 | Bathroom\bath_100.jpg  | Bathroom\bath_1003.jpg | Dinning\din_1593.jpg       |
 | Bathroom\bath_1003.jpg | Bathroom\bath_1004.jpg | Bedroom\bed_329.jpg        |
 | Bathroom\bath_1004.jpg | Bathroom\bath_1005.jpg | Livingroom\living_1030.jpg |
 | Bathroom\bath_1005.jpg | Bathroom\bath_1007.jpg | Bedroom\bed_1240.jpg       |
 +------------------------+------------------------+----------------------------+

triplets.info(memory_usage="deep")
 
 #   Column   Non-Null Count   Dtype  
 # --- ------   --------------   -----  
 # 0   anchor   525000 non-null category
 # 1   positive 525000 non-null category
 # 2   negative 525000 non-null category
 # dtypes: category(3)
 # memory usage: 4.6 MB
 
 # without categories
 triplets_raw.info(memory_usage="deep")
 
 #   Column   Non-Null Count   Dtype
 # --- ------   --------------   -----
 # 0   anchor   525000 non-null object
 # 1   positive 525000 non-null object
 # 2   negative 525000 non-null object
 # dtypes: object(3)
 # memory usage: 118.1 MB

cols = sorted([col for col in original_df.columns \
               if col.startswith("pct_bb")])
 df = original_df[(["cfips"] + cols)]
 df = df.melt(id_vars="cfips",
              value_vars=cols,
              var_name="year",
              value_name="feature").sort_values(by=["cfips", "year"])

import pandas as pd
 import swifter
 
 def target_function(row):
     return row * 10
 
 def traditional_way(data):
     data['out'] = data['in'].apply(target_function)
 
 def swifter_way(data):
     data['out'] = data['in'].swifter.apply(target_function)

import pandas as pd
 from pandarallel import pandarallel
 
 def target_function(row):
     return row * 10
 
 def traditional_way(data):
     data['out'] = data['in'].apply(target_function)
 
 def pandarallel_way(data):
     pandarallel.initialize()
     data['out'] = data['in'].parallel_apply(target_function)

|        file            |  size   |
 +------------------------+---------+
 | triplets_525k.csv      | 38.4 MB |
 | triplets_525k.csv.gzip |  4.3 MB |
 | triplets_525k.csv.zip  |  4.5 MB |
 | triplets_525k.parquet  |  1.9 MB |
 +------------------------+---------+

df = pd.DataFrame({"a": [1, 2, None], "b": [4., 5.1, 14.02]})
 df["a"] = df["a"].astype("Int64")
 print(df.info())
 print(df["a"].value_counts(normalize=True, dropna=False),
      df["a"].value_counts(normalize=True, dropna=True), sep="\n\n")

!pip install modin[all]
 
 import modin.pandas as pd
 df = pd.read_csv("my_dataset.csv")

import pandas as pd
 
 regex = (r'(?P