Pandasticsearch: An Elasticsearch client exposing DataFrame API

# Create a DataFrame object

from pandasticsearch import DataFrame

df = DataFrame.from_es('http://localhost:9200', index='people')



# Print the schema(mapping) of the index

df.print_schema()

# company

# |-- employee

#   |-- name: {'index': 'not_analyzed', 'type': 'string'}

#   |-- age: {'type': 'integer'}

#   |-- gender: {'index': 'not_analyzed', 'type': 'string'}



# Inspect the columns

df.columns

#['name', 'age', 'gender']



# Get the column

df.name

# Column('name')



# Filter

df.filter(df.age < 13).collect()

# [Row(age=12,gender='female',name='Alice'), Row(age=11,gender='male',name='Bob')]



# Project

df.filter(df.age < 25).select('name', 'age').collect()

# [Row(age=12,name='Alice'), Row(age=11,name='Bob'), Row(age=13,name='Leo')]



# Print the rows into console

df.filter(df.age < 25).select('name').show(3)

# +------+

# | name |

# +------+

# | Alice|

# | Bob  |

# | Leo  |

# +------+



# Sort

df.sort(df.age.asc).select('name', 'age').collect()

#[Row(age=11,name='Bob'), Row(age=12,name='Alice'), Row(age=13,name='Leo')]



# Aggregate

df[df.gender == 'male'].agg(df.age.avg).collect()

# [Row(avg(age)=12)]



# Groupby

df.groupby('gender').collect()

# [Row(doc_count=1), Row(doc_count=2)]



# Groupby and then aggregate

df.groupby('gender').agg(df.age.max).collect()

# [Row(doc_count=1, max(age)=12), Row(doc_count=2, max(age)=13)]



# Convert to Pandas object for subsequent analysis

df[df.gender == 'male'].agg(df.age.avg).to_pandas()

#    avg(age)

# 0        12