GuidoTournois

GuidoTournois

GuidoTournois

import pandas
from sklearn.linear_model import LogisticRegression
datafile = "data.csv"
chunksize = 100000
models = []
for chunk in pd.read_csv(datafile, chunksize=chunksize):
    chunk = pre_process_and_feature_engineer(chunk) 
    # A function to clean my data and create my features
    model = LogisticRegression()
    model.fit(chunk[features], chunk['label'])

GuidoTournois

import pandas
import random

filename = "data.csv" 
n = sum(1 for line in open(filename))-1  # Calculate number of rows in file
s = n//10  # sample size of 10%
skip = sorted(random.sample(range(1, n+1), n-s))  # n+1 to compensate for header 
df = pandas.read_csv(filename, skiprows=skip)