#!/usr/bin/env python
# coding: utf-8

# ## Iris Data

# > 📢: **This document was used during early development of siuba. See the [select docs](https://siuba.readthedocs.io/en/latest/api_table_core/03_select.html).**
# 
# Many different ways of selecting columns from the iris dataset. 

# In[1]:


from siuba import *
import pandas as pd

pd.set_option('max_rows', 5)


# In[2]:


## Rather than import the iris data from sklearn, I am just including the
## first 5 rows.

# from sklearn import datasets
# iris = datasets.load_iris()
# df_iris = pd.DataFrame(iris.data, columns = iris.feature_names)
# df_iris['species'] = iris.target_names[iris.target]

df_iris = pd.DataFrame({
    'sepal length (cm)': [5.1, 4.9, 4.7, 4.6, 5.0],
    'sepal width (cm)': [3.5, 3.0, 3.2, 3.1, 3.6],
    'petal length (cm)': [1.4, 1.4, 1.3, 1.5, 1.4],
    'petal width (cm)': [0.2, 0.2, 0.2, 0.2, 0.2],
    'species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa']
})


# In[3]:


# get sepal columns
select(df_iris, _.startswith("sepal"))

# get width measure columns
# note method calls sent to df_iris.columns.str
# so _.endswith("...") is equivalent to df_iris.columns.str.endswith("...")
select(df_iris, _.endswith("width (cm)"))

# movie species to front
# _.endswith("") is a hack to get everything
select(df_iris, _.species, _.endswith(""))

# move sepal length to the back
# first select all variables except Sepal.Length, then re select Sepal.Length
select(df_iris, -_["sepal length (cm)"], _["sepal length (cm)"])


# ## Wide table

# In[4]:


import numpy as np
from numpy.random import uniform, seed

seed(123)

df = pd.DataFrame(uniform(size = [10, 10]))
df = df[np.array([3, 4, 7, 1, 9, 8, 5, 2, 6, 10]) - 1]
df.columns = "V" + df.columns.astype(str)
df


# In[5]:


select(df, _["V3":"V5"])
#select(df, _["V5":"V3"])

# no num_range capability


# In[6]:


# can exclude matches
select(df_iris, -_.startswith("petal"))


# In[7]:


# select can grab specific and rename columns
select(df_iris, _.petal_length == _["petal length (cm)"])

# rename leaves all columns
rename(df_iris, petal_length = "petal length (cm)")


# In[8]:


# Uh--- TODO? should return error? In tidyverse does group rename
# pretty rare to see!
#select(df_iris, _.obs == _.startswith('s'))