I'm trying to shuffle my indices using the np.random.shuffle() method, but I keep getting an error that I don't understand. I'd really appreciate it if someone could help me puzzle this out. Thank you!
Here is my code:
#Goal: Preprocess the Data to Predict Excessive Employee absence
#Import Libraries
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
raw_csv_data= pd.read_csv('Absenteeism-data.csv')
print(raw_csv_data)
df= raw_csv_data.copy()
print(display(df))
pd.options.display.max_columns=None
pd.options.display.max_rows=None
print(display(df))
print(df.info())
df=df.drop(['ID'], axis=1)
print(display(df.head()))
#Our goal is to see who is more likely to be absent. Let's define
#our targets from our dependent variable, Absenteeism Time in Hours
print(df['Absenteeism Time in Hours'])
print(df['Absenteeism Time in Hours'].median())
targets= np.where(df['Absenteeism Time in Hours']>df['Absenteeism
Time in Hours'].median(),1,0)
print(targets)
df['Excessive Absenteeism']= targets
print(df.head())
#Let's Separate the Day and Month Values to see if there is
correlation
#between Day of week/month with absence
print(type(df['Date'][0]))
df['Date']= pd.to_datetime(df['Date'], format='%d/%m/%Y')
print(df['Date'])
print(type(df['Date'][0]))
#Extracting the Month Value
print(df['Date'][0].month)
list_months=[]
print(list_months)
print(df.shape)
for i in range(df.shape[0]):
list_months.append(df['Date'][i].month)
print(list_months)
print(len(list_months))
#Let's Create a Month Value Column for df
df['Month Value']= list_months
print(df.head())
#Now let's extract the day of the week from date
df['Date'][699].weekday()
def date_to_weekday(date_value):
return date_value.weekday()
df['Day of the Week']= df['Date'].apply(date_to_weekday)
print(df.head())
df= df.drop(['Date'], axis=1)
print(df.columns.values)
reordered_columns= ['Reason for Absence', 'Month Value','Day of the
Week','Transportation Expense', 'Distance to Work', 'Age',
'Daily Work Load Average', 'Body Mass Index', 'Education',
'Children', 'Pets',
'Absenteeism Time in Hours', 'Excessive Absenteeism']
df=df[reordered_columns]
print(df.head())
#First Checkpoint
df_date_mod= df.copy()
print(df_date_mod)
#Let's Standardize our inputs, ignoring the Reasons and Education
Columns
#Because they are labelled by a separate categorical criteria, not
numerically
print(df_date_mod.columns.values)
unscaled_inputs= df_date_mod.loc[:, ['Month Value','Day of the
Week','Transportation Expense','Distance to Work','Age','Daily Work
Load Average','Body Mass Index','Children','Pets','Absenteeism Time
in Hours']]
print(display(unscaled_inputs))
absenteeism_scaler= StandardScaler()
absenteeism_scaler.fit(unscaled_inputs)
scaled_inputs= absenteeism_scaler.transform(unscaled_inputs)
print(display(scaled_inputs))
print(scaled_inputs.shape)
scaled_inputs= pd.DataFrame(scaled_inputs, columns=['Month
Value','Day of the Week','Transportation Expense','Distance to
Work','Age','Daily Work Load Average','Body Mass
Index','Children','Pets','Absenteeism Time in Hours'])
print(display(scaled_inputs))
df_date_mod= df_date_mod.drop(['Month Value','Day of the
Week','Transportation Expense','Distance to Work','Age','Daily Work
Load Average','Body Mass Index','Children','Pets','Absenteeism Time
in Hours'], axis=1)
print(display(df_date_mod))
df_date_mod=pd.concat([df_date_mod,scaled_inputs], axis=1)
print(display(df_date_mod))
df_date_mod= df_date_mod[reordered_columns]
print(display(df_date_mod.head()))
#Checkpoint
df_date_scale_mod= df_date_mod.copy()
print(display(df_date_scale_mod.head()))
#Let's Analyze the Reason for Absence Category
print(df_date_scale_mod['Reason for Absence'])
print(df_date_scale_mod['Reason for Absence'].min())
print(df_date_scale_mod['Reason for Absence'].max())
print(df_date_scale_mod['Reason for Absence'].unique())
print(len(df_date_scale_mod['Reason for Absence'].unique()))
print(sorted(df['Reason for Absence'].unique()))
reason_columns= pd.get_dummies(df['Reason for Absence'])
print(reason_columns)
reason_columns['check']= reason_columns.sum(axis=1)
print(reason_columns)
print(reason_columns['check'].sum(axis=0))
print(reason_columns['check'].unique())
reason_columns=reason_columns.drop(['check'], axis=1)
print(reason_columns)
reason_columns=pd.get_dummies(df_date_scale_mod['Reason for
Absence'], drop_first=True)
print(reason_columns)
#%%
print(df_date_scale_mod.columns.values)
print(reason_columns.columns.values)
df_date_scale_mod= df_date_scale_mod.drop(['Reason for Absence'],
axis=1)
print(df_date_scale_mod)
reason_type_1= reason_columns.loc[:, 1:14].max(axis=1)
reason_type_2= reason_columns.loc[:, 15:17].max(axis=1)
reason_type_3= reason_columns.loc[:, 18:21].max(axis=1)
reason_type_4= reason_columns.loc[:, 22:].max(axis=1)
print(reason_type_1)
print(reason_type_2)
print(reason_type_3)
print(reason_type_4)
print(df_date_scale_mod.head())
df_date_scale_mod= pd.concat([df_date_scale_mod,
reason_type_1,reason_type_2, reason_type_3, reason_type_4], axis=1)
print(df_date_scale_mod.head())
print(df_date_scale_mod.columns.values)
column_names= ['Month Value','Day of the Week','Transportation
Expense',
'Distance to Work','Age','Daily Work Load Average','Body Mass
Index',
'Education','Children','Pets','Absenteeism Time in Hours',
'Excessive Absenteeism', 'Reason_1', 'Reason_2', 'Reason_3',
'Reason_4']
df_date_scale_mod.columns= column_names
print(df_date_scale_mod.head())
column_names_reordered= ['Reason_1', 'Reason_2', 'Reason_3',
'Reason_4','Month Value','Day of the Week','Transportation Expense',
'Distance to Work','Age','Daily Work Load Average','Body Mass
Index',
'Education','Children','Pets','Absenteeism Time in Hours',
'Excessive Absenteeism']
df_date_scale_mod=df_date_scale_mod[column_names_reordered]
print(display(df_date_scale_mod.head()))
#Checkpoint
df_date_scale_mod_reas= df_date_scale_mod.copy()
print(df_date_scale_mod_reas.head())
#Let's Look at the Education column now
print(df_date_scale_mod_reas['Education'].unique())
#This shows us that education is rated from 1-4 based on level
#of completion
print(df_date_scale_mod_reas['Education'].value_counts())
#The overwhelming majority of workers are highschool educated, while
the rest have higher degrees
#We'll create our dummy variables as highschool and higher education
df_date_scale_mod_reas['Education']=
df_date_scale_mod_reas['Education'].map({1:0, 2:1, 3:1, 4:1})
print(df_date_scale_mod_reas['Education'].unique())
print(df_date_scale_mod_reas['Education'].value_counts())
#Checkpoint
df_preprocessed= df_date_scale_mod_reas.copy()
print(display(df_preprocessed.head()))
#Split Inputs from targets
scaled_inputs_all= df_preprocessed.loc[:,'Reason_1':'Absenteeism
Time in Hours']
print(display(scaled_inputs_all.head()))
print(scaled_inputs_all.shape)
targets_all= df_preprocessed.loc[:,'Excessive Absenteeism']
print(display(targets_all.head()))
print(targets_all.shape)
#Shuffle Inputs and targets
shuffled_indices= np.arange(scaled_inputs_all.shape[0])
np.random.shuffle(shuffled_indices)
shuffled_inputs= scaled_inputs_all[shuffled_indices]
shuffled_targets= targets_all[shuffled_indices]
Here is the error:
KeyError Traceback (most recent call last)
in
1 shuffled_indices= np.arange(scaled_inputs_all.shape[0])
2 np.random.shuffle(shuffled_indices)
----> 3 shuffled_inputs= scaled_inputs_all[shuffled_indices]
4 shuffled_targets= targets_all[shuffled_indices]
~\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
2932 key = list(key)
2933 indexer = self.loc._convert_to_indexer(key, axis=1,
-> 2934 raise_missing=True)
2935
2936 # take() does not accept boolean indexers
~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _convert_to_indexer(self, obj, axis, is_setter, raise_missing)
1352 kwargs = {'raise_missing': True if is_setter else
1353 raise_missing}
-> 1354 return self._get_listlike_indexer(obj, axis, **kwargs)[1]
1355 else:
1356 try:
~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _get_listlike_indexer(self, key, axis, raise_missing)
1159 self._validate_read_indexer(keyarr, indexer,
1160 o._get_axis_number(axis),
-> 1161 raise_missing=raise_missing)
1162 return keyarr, indexer
1163
~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _validate_read_indexer(self, key, indexer, axis, raise_missing)
1244 raise KeyError(
1245 u"None of [{key}] are in the [{axis}]".format(
-> 1246 key=key, axis=self.obj._get_axis_name(axis)))
1247
1248 # We (temporarily) allow for some missing keys with .loc, except in
KeyError: "None of [Int64Index([560, 320, 405, 141, 154, 370, 656, 26, 444, 307,\n ...\n 429, 542, 676, 588, 315, 284, 293, 607, 197, 250],\n dtype='int64', length=700)] are in the [columns]"
What I have tried:
I've tried to use the delimiter=',' and delim_whitespace=0 (two solutions that i didn't understand anyway) when I made my raw_csv_data variable at the beginning, as I saw that as the solution of another problem, but it kept throwing the same error