“Lesen Sie große SAS -Datei illarger als Speicher n Python” Code-Antworten

Lesen Sie große SAS -Datei illarger als Speicher n Python

import pandas as pd
import pyreadstat
filename = 'foo.SAS7BDAT'
CHUNKSIZE = 50000
offset = 0
allChunk,_ = getChunk(row['filePath'], row_limit=CHUNKSIZE, row_offset=offset)
allChunk = allChunk.astype('category')

while True:
    offset += CHUNKSIZE
    # for xpt data, use pyreadstat.read_xpt()
    chunk, _ = pyreadstat.read_sas7bdat(filename, row_limit=CHUNKSIZE, row_offset=offset)
    if chunk.empty: break  # if chunk is empty, it means the entire data has been read, so break

    for eachCol in chunk:  #converting each column to categorical 
        colUnion = pd.api.types.union_categoricals([allChunk[eachCol], chunk[eachCol]])
        allChunk[eachCol] = pd.Categorical(allChunk[eachCol], categories=colUnion.categories)
        chunk[eachCol] = pd.Categorical(chunk[eachCol], categories=colUnion.categories)

    allChunk = pd.concat([allChunk, chunk])  #Append each chunk to the resulting dataframe