josepablog

from sklearn.feature_extraction import DictVectorizer
import pandas as pd

df = pd.DataFrame({"user_name": ["a", "b", "c"]})
fe_lm = DictVectorizer()
design_lm = fe_lm.fit_transform(df.to_dict(orient="records"))

# Note that this solution is *MUCH* faster (60 times) than transposing and converting into a dictionary:
# http://fastml.com/converting-categorical-data-into-numbers-with-pandas-and-scikit-learn/ is much slower

josepablog

import gzip
from functools import wraps
import boto3
from sqlalchemy import MetaData
from pandas import DataFrame
from pandas.io.sql import SQLTable, pandasSQL_builder
import psycopg2
import codecs
import cStringIO
from io import  BytesIO