koalas_dataframe_creation_viewing_sorting_quickstart.py

1import pandas as pd
2import numpy as np
3import databricks.koalas as ks
4from pyspark.sql import SparkSession
5
6# Object Creation
7# Creating a Koalas Series by passing a list of values
8s = ks.Series([1, 3, 5, np.nan, 6, 8])
9
10# Creating a Koalas DataFrame by passing a dict of objects that can be converted to series-like.
11kdf = ks.DataFrame(
12    {'a': [1, 2, 3, 4, 5, 6],
13     'b': [100, 200, 300, 400, 500, 600],
14     'c': ["one", "two", "three", "four", "five", "six"]},
15    index=[10, 20, 30, 40, 50, 60])
16
17# Viewing Data
18# See the top rows of the frame
19print(kdf.head())
20
21# Display the index, columns, and the underlying numpy data
22print(kdf.index)
23print(kdf.columns)
24print(kdf.to_numpy())
25
26# Describe shows a quick statistic summary of your data
27print(kdf.describe())
28
29# Transposing your data
30print(kdf.T)
31
32# Sorting by an axis
33print(kdf.sort_index(ascending=False))
34
35# Sorting by values
36print(kdf.sort_values(by='b'))