# jupytext_version: 1.6.0
# kernelspec:
# display_name: Python 3
# language: python
# name: python3
# ---
# + [markdown] papermill={"duration": 0.092568, "end_time": "2020-08-07T07:17:20.608866", "exception": false, "start_time": "2020-08-07T07:17:20.516298", "status": "completed"} tags=[]
# # PyCaret 2 Regression Example
# - https://github.com/pycaret/pycaret/blob/master/examples/PyCaret%202%20Regression.ipynb
# + execution={"iopub.execute_input": "2020-08-07T07:17:20.800167Z", "iopub.status.busy": "2020-08-07T07:17:20.799149Z", "iopub.status.idle": "2020-08-07T07:17:20.827968Z", "shell.execute_reply": "2020-08-07T07:17:20.828775Z"} papermill={"duration": 0.127113, "end_time": "2020-08-07T07:17:20.829021", "exception": false, "start_time": "2020-08-07T07:17:20.701908", "status": "completed"} tags=[]
# check version
from pycaret.utils import version
version()
# + execution={"iopub.execute_input": "2020-08-07T07:17:21.220348Z", "iopub.status.busy": "2020-08-07T07:17:21.219385Z", "iopub.status.idle": "2020-08-07T07:17:28.141603Z", "shell.execute_reply": "2020-08-07T07:17:28.140751Z"} papermill={"duration": 7.02273, "end_time": "2020-08-07T07:17:28.141797", "exception": false, "start_time": "2020-08-07T07:17:21.119067", "status": "completed"} tags=[]
# %reload_ext autoreload
# %autoreload 2
# %matplotlib inline
from IPython.core.display import display, HTML
display(
HTML("<style>.container { width:96% !important; }</style>")) # デフォルトは75%
import os
import sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import urllib.request
# display imports
from IPython.display import display, IFrame
from IPython.core.display import HTML
# import notebook styling for tables and width etc.
response = urllib.request.urlopen(
'https://raw.githubusercontent.com/DataScienceUWL/DS775v2/master/ds755.css'
)
HTML(response.read().decode("utf-8"))
import os
# check version
from pycaret.utils import version
print(version())
def missing_values_table(df):
mis_val = df.isnull().sum()
mis_val_percent = 100 * df.isnull().sum() / len(df)
mis_val_table = pd.concat([mis_val, mis_val_percent], axis=1)
mis_val_table_ren_columns = mis_val_table.rename(columns={
0: 'Missing Values',
1: '% of Total Values'
})
mis_val_table_ren_columns = mis_val_table_ren_columns[
mis_val_table_ren_columns.iloc[:, 1] != 0].sort_values(
'% of Total Values', ascending=False).round(1)
print("Your selected dataframe has " + str(df.shape[1]) + " columns.\n"
"There are " + str(mis_val_table_ren_columns.shape[0]) +
