Classifier
Csv
p27 Import a comma-separated values (CSV) file.
""" Read CSV
The source can be URL or FILE
"""
import pandas as pd
import pathlib
# Read from URL
URL = 'https://raw.githubusercontent.com/chrisalbon/sim_data/master/data.csv'
dataframe = pd.read_csv(URL)
# Read from FILE
DIR = pathlib.Path(__file__).resolve().parent
dataframe = pd.read_csv(DIR / '../_data/01.csv')
print(dataframe.head(2).to_markdown())
# | | integer | datetime | category |
# |---:|----------:|:--------------------|-----------:|
# | 0 | 5 | 2015-01-01 00:00:00 | 0 |
# | 1 | 5 | 2015-01-01 00:00:01 | 0 |
Excel
p28 Import an Excel spreadsheet.
""" Read Excel
Import an Excel spreadsheet
pip install openpyxl
"""
import pandas as pd
import pathlib
FILE = pathlib.Path(__file__).resolve().parent / '../_data/02.xlsx'
df = pd.read_excel(FILE , sheet_name=0)
print(df.head(2).to_markdown())
# | | integer | datetime | category |
# |---:|----------:|:--------------------|-----------:|
# | 0 | 5 | 2015-01-01 00:00:00 | 0 |
# | 1 | 5 | 2015-01-01 00:00:01 | 0 |
Json
p29 Load a JSON file for data preprocessing.
""" Read Json
Load a JSON file for data preprocessing.
"""
import pandas as pd
import pathlib
FILE = pathlib.Path(__file__).resolve().parent / '../_data/03.json'
df = pd.read_json(FILE, orient='columns')
print(df.head(2).to_markdown())
# | | integer | datetime | category |
# |---:|----------:|:--------------------|-----------:|
# | 0 | 5 | 2015-01-01 00:00:00 | 0 |
# | 1 | 5 | 2015-01-01 00:00:01 | 0 |
# Json normalize
DATA = [
{
"id": 1,
"name": "Mary",
},
{
"id": 2,
"name": "John",
},
]
df = pd.json_normalize(DATA)
print(df.head(2).to_markdown())
# | | id | name |
# |---:|-----:|:-------|
# | 0 | 1 | Mary |
# | 1 | 2 | John |
Sql
p30 Probably the most used method in real world.
""" Read SQL Database
Load data from a database using SQL queries.
Probably the most used in real world.
"""
import pandas as pd
import sqlite3
import pathlib
DIR = pathlib.Path(__file__).resolve().parent
conn = sqlite3.connect(DIR / '../_data/04.db')
df = pd.read_sql_query("SELECT * FROM data", conn)
print(df.head(2).to_markdown())
# | | first_name | last_name | age | preTestScore | postTestScore |
# |---:|:-------------|:------------|------:|---------------:|----------------:|
# | 0 | Jason | Miller | 42 | 4 | 25 |
# | 1 | Molly | Jacobson | 52 | 24 | 94 |
➥ Questions
Last update: 45 days ago
