How to set/get Pandas dataframes into Redis using pyarrow

Question

Using

dd = {'ID': ['H576','H577','H578','H600', 'H700'],
      'CD': ['AAAAAAA', 'BBBBB', 'CCCCCC','DDDDDD', 'EEEEEEE']}
df = pd.DataFrame(dd)

Pre Pandas 0.25, this below worked.

set:  redisConn.set("key", df.to_msgpack(compress='zlib'))
get:  pd.read_msgpack(redisConn.get("key"))

Now, there are deprecated warnings..

FutureWarning: to_msgpack is deprecated and will be removed in a future version.
It is recommended to use pyarrow for on-the-wire transmission of pandas objects.

The read_msgpack is deprecated and will be removed in a future version.
It is recommended to use pyarrow for on-the-wire transmission of pandas objects.

How does pyarrow work? And, how do I get pyarrow objects into and back from Redis.

reference: How to set/get pandas.DataFrame to/from Redis?

Answer 1

Here's a full example to use pyarrow for serialization of a pandas dataframe to store in redis

apt-get install python3 python3-pip redis-server
pip3 install pandas pyarrow redis

and then in python

import pandas as pd
import pyarrow as pa
import redis

df=pd.DataFrame({'A':[1,2,3]})
r = redis.Redis(host='localhost', port=6379, db=0)

context = pa.default_serialization_context()
r.set("key", context.serialize(df).to_buffer().to_pybytes())
context.deserialize(r.get("key"))
   A
0  1
1  2
2  3

I just submitted PR 28494 to pandas to include this pyarrow example in the docs.

Reference docs:

• https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.to_msgpack.html
• https://arrow.apache.org/docs/python/ipc.html#arbitrary-object-serialization
• https://arrow.apache.org/docs/python/memory.html#pyarrow-buffer
• https://stackoverflow.com/a/37957490/4126114

Answer 2

If you would like to compress the data in Redis, you can use the built in support for parquet & gzip

def openRedisCon():
   pool = redis.ConnectionPool(host=REDIS_HOST, port=REDIS_PORT, db=0)
   r = redis.Redis(connection_pool=pool)
   return r

def storeDFInRedis(alias, df):
    """Store the dataframe object in Redis
    """

    buffer = io.BytesIO()
    df.to_parquet(buffer, compression='gzip')
    buffer.seek(0) # re-set the pointer to the beginning after reading
    r = openRedisCon()
    res = r.set(alias,buffer.read())

def loadDFFromRedis(alias, useStale: bool = False):
    """Load the named key from Redis into a DataFrame and return the DF object
    """

    r = openRedisCon()

    try:
        buffer = io.BytesIO(r.get(alias))
        buffer.seek(0)
        df = pd.read_parquet(buffer)
        return df
    except:
        return None

Answer 3

Pickle and zlib can be an alternative to pyarrow:

import pandas as pd
import redis
import zlib
import pickle

df=pd.DataFrame({'A':[1,2,3]})
r = redis.Redis(host='localhost', port=6379, db=0)
r.set("key", zlib.compress( pickle.dumps(df)))
df=pickle.loads(zlib.decompress(r.get("key")))

Answer 4

import pandas as pd
import redis
import pickle

r = redis.Redis(host='localhost', port=6379, db=0)

data = {
    "calories": ["v1", 'v2', 'v3'],
    "duration": [50, 40, 45]
}
df = pd.DataFrame(data, index=["day1", "day2", "day3"])

r.set("key", pickle.dumps(df))
print(pickle.loads(r.get("key")))

alternatively, you can use direct-redis

import pandas as pd
from direct_redis import DirectRedis

r = DirectRedis(host='localhost', port=6379)
>>> df =  pd.DataFrame([[1,2,3,'235', '@$$#@'], 
                   ['a', 'b', 'c', 'd', 'e']])
>>> print(df)
   0  1  2    3      4
0  1  2  3  235  @$$#@
1  a  b  c    d      e   

>>> r.set('df', df)   

>>> r.get('df')
   0  1  2    3      4
0  1  2  3  235  @$$#@
1  a  b  c    d      e   

>>> type(r.get('df'))
<class 'pandas.core.frame.DataFrame'>

Answer 5

import pandas as pd
import pyarrow as pa
import redis


r = redis.Redis(host=REDIS_HOST, port=REDIS_PORT, db=0)


def save_df_to_redis(r, redis_key, df):
    buffer = pa.serialize_pandas(df)
    r.set(redis_key, buffer.to_pybytes())


def load_df_from_redis(r, redis_key):
    buffer = r.get(redis_key)
    df = pa.deserialize_pandas(buffer)
    return df



data = {
    "Name": ["John", "Anna", "Peter"],
    "Age": [28, 24, 33],
}
df = pd.DataFrame(data)

save_df_to_redis(r, "key", df)
df_redis = load_df_from_redis(r, "key")
print(df_redis)

Answer 6

You can try this as well, if you set decode_response to true in Redis python client.

to_save = value.to_string()
r.set(redis_key, to_save)

value = r.get(redis_key)
df = pd.read_csv(io.StringIO(value))

Answer 7

Here is how I do it since default_serialization_context is deprecated and things are a bit simpler:

import pyarrow as pa
import redis

pool = redis.ConnectionPool(host='localhost', port=6379, db=0)
r = redis.Redis(connection_pool=pool)

def storeInRedis(alias, df):
    df_compressed = pa.serialize(df).to_buffer().to_pybytes()
    res = r.set(alias,df_compressed)
    if res == True:
        print(f'{alias} cached')

def loadFromRedis(alias):
    data = r.get(alias)
    try:
        return pa.deserialize(data)
    except:
        print("No data")


storeInRedis('locations', locdf)

loadFromRedis('locations')