#
Data loading
import pandas as pd
import numpy as np
import json
import lxml
from sklearn import datasets
#
JSON Data
obj = """
{"name": "Wes",
"cities_lived": ["Akron", "Nashville", "New York", "San Francisco"],
"pet": null,
"siblings": [{"name": "Scott", "age": 34, "hobbies": ["guitars", "soccer"]},
{"name": "Katie", "age": 42, "hobbies": ["diving", "art"]}]
}
"""
res = json.loads(obj) # To dict
res
{'name': 'Wes',
'cities_lived': ['Akron', 'Nashville', 'New York', 'San Francisco'],
'pet': None,
'siblings': [{'name': 'Scott', 'age': 34, 'hobbies': ['guitars', 'soccer']},
{'name': 'Katie', 'age': 42, 'hobbies': ['diving', 'art']}]}
res = json.dumps(res) # To str
res
'{"name": "Wes", "cities_lived": ["Akron", "Nashville", "New York", "San Francisco"], "pet": null, "siblings": [{"name": "Scott", "age": 34, "hobbies": ["guitars", "soccer"]}, {"name": "Katie", "age": 42, "hobbies": ["diving", "art"]}]}'
#
XML
lxml.objectify.parse(file)
#
Binary
df = datasets.load_iris(as_frame=True).frame
df
sepal length (cm) | sepal width (cm) | petal length (cm) | petal width (cm) | target | |
---|---|---|---|---|---|
0 | 5.1 | 3.5 | 1.4 | 0.2 | 0 |
1 | 4.9 | 3.0 | 1.4 | 0.2 | 0 |
2 | 4.7 | 3.2 | 1.3 | 0.2 | 0 |
3 | 4.6 | 3.1 | 1.5 | 0.2 | 0 |
4 | 5.0 | 3.6 | 1.4 | 0.2 | 0 |
... | ... | ... | ... | ... | ... |
145 | 6.7 | 3.0 | 5.2 | 2.3 | 2 |
146 | 6.3 | 2.5 | 5.0 | 1.9 | 2 |
147 | 6.5 | 3.0 | 5.2 | 2.0 | 2 |
148 | 6.2 | 3.4 | 5.4 | 2.3 | 2 |
149 | 5.9 | 3.0 | 5.1 | 1.8 | 2 |
150 rows × 5 columns
df.to_pickle('a')
pd.read_pickle('a')