pandas-nosql-0.0.2.tar.gz

# Pandas-NoSQL __Pandas-NoSQL adds read and write capabilities to pandas for several nosql databases__ --- Import the pandas_nosql module to add read and write methods for: * MongoDB * Elasticsearch * Redis * Apache Cassandra ## MongoDB ```python # Read a MongoDB collection into a DataFrame # Defaults: host='localhost' port=27017 # For nested collections use normalize=True import pandas as pd import pandas_nosql df = pd.read_mongo(database='test_db', collection='test_col', normalize=True) # Write DataFrame to MongoDB collection # modify_colletion parameter is to help prevent accidental overwrites df.to_mongo(database='test_db', collection='test_col2', modify_collection=True) ``` ## Elasticsearch ```python import pandas as pd import pandas_nosql # Read an Elastic index into a DataFrame # Defaults: # * hosts='https://localhost:9200' # * verify_certs=False # To split out _source use normalize=True elastic_cols = ('make', 'model', 'purchase_date', 'miles') df = pd.read_elastic( hosts='https://localhost:9200', username='elastic', password='strong_password', index='test_index', fields=elastic_cols, verify_certs=False normalize=True ) # Write DataFrame to Elastic Index df.to_elastic( hosts='https://localhost:9200', username='elastic', password='strong_password', index='test_index', create_index=True ) ``` ## Redis ```python import pandas as pd import pandas_nosql # Read a DataFrame that was sent to Redis using the to_redis method # A DataFrame not sent to Redis using the to_redis method is not guaranteed to be read properly # Defaults: # * host='localhost' # * expire_seconds=None # To persist the DataFrame in Redis use expire_seconds=None # To set an expiration for the DataFrame pass an integer to expire_seconds df = pd.read_redis(host='localhost', port=6379, redis_key='test_key', expire_seconds=None) # Write a DataFrame to Redis df.to_redis(host='localhost', port=6379, redis_key='test_key') ``` ## Apache Cassandra ```python import pandas as pd import pandas_nosql # Read an Apache Cassandra table into a Panda DataFrame # contact_points must be a list df = pd.read_cassandra( contact_points=['localhost'], port=9042, keyspace='test_keyspace', table='test_table' ) # Append a DataFrame to Apache Cassandra # DataFrame Columns must match table Columns df.to_cassandra( contact_points=['localhost'], port=9042, keyspace='test_keyspace', table='test_table' ) ```