Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work
Questions tagged [feature-engineering]
481 questions
-1
votes
1 answer
Machine Learning：Structuring features for classification when multiple rows belong to the same ID
Here is my problem:
For example, I have a table contains people's behavior information in a month (multiple features), each person has a unique ID and a unique label (0 and 1). What I want to do is using these features to predict whether a customer…
WWH98932
- 123
- 1
- 1
- 9
-2
votes
1 answer
One hot encoding training and test data
I am working on the "House Prices - Advanced Regression Techniques" machine learning problem. They provide training data and test data. I have to create a model that will predict the house prices of the test set.
There are many features in my train…
Py_Student
- 163
- 1
- 12
-2
votes
1 answer
Feature extraction package for time-sereis
What are the different packages available for feature extraction when dealing with time-series data ?
I am aware about TSFRESH package. Any other package which is better than the mentioned one.
I have searched different blogs but not sure which one…
deep kachhawa
- 3
- 3
-2
votes
2 answers
Separating text in r
I have a data.frame that contains a column named movies_name. this column contain data as in this format: City of Lost Children, The (Cité des enfants perdus, La) (1995) I want to separate the year from the rest of the movie name without losing the…
Nada Abbas
- 3
- 4
-2
votes
1 answer
Feature engineering: first sum, then take the logarithm, or the other way around?
I'm doing some feature engineering for my data. Each datapoint is a set of values, namely transaction amounts for a customers account. I need to create only one feature for each set, for example, I take the maximum, mean, minimum and other…
Michaela Mašková
- 7
- 4
-2
votes
1 answer
Feature scaling on null values
How to handle null values in dataset for performing feature scaling on a particular column?
That is to say, should we keep the null value as it is, or impute some value?
Is there any tutorial on how to handle null values while feature scaling?
Pratik Goud
- 1
- 2
-2
votes
1 answer
Feature engineering, ValueError: Columns must be same length as key
I'm running into a ValueError: Columns must be same length as key when trying to do encoding for the column Type. Here are the codes, not sure which part is wrong.
df.head()
plt.figure(figsize=(7, 5))
sns.heatmap(df.isnull(),…
Leo
- 93
- 2
- 11
-2
votes
2 answers
Feature engineering with dirty data
I have this assignment where I need to clean up the data and do feature engineering on a dataset but the data itself is very dirty as some of the data is shifted (on the wrong columns), or NULL. How can I clean up the data all using python? I'm not…
Nic
- 1
-3
votes
1 answer
Creating domain expertise features as feature-engineering methods
can you explain to me what is the method of (Creating domain expertise features)? I have already read a paper that they mentioned this as as method of feature engineering. this is the link of…
mahsa
- 1
- 1
-3
votes
1 answer
which feature selection technique would be suitable for this dataset
i want to do binary classification with this dataset
dataset is numerical and i am manually adding "class" feature to the dataset with binary values (0,1) or (benign, malicious) depends on either feature selection technique require numerical or…
Zara
- 1
- 3
-3
votes
1 answer
I want to create new variable with the help of existing variable
I have data with variable name as "sales enquiry date", "sales enquiry stage"
i want to create a new variable "current stage date"
so example enquirer date is 10/03/2017 and stage is Meeting,
similarly, enquirer date is 27/04/2017 and stage is…
analytics leadge
- 11
- 3
-3
votes
1 answer
What does this code means in R? full$Title <- gsub('(.*, )|(\\..*)', '', full$Name)
```{r, message=FALSE, warning=FALSE}
# Grab title from passenger names
full$Title <- gsub('(.*, )|(\\..*)', '', full$Name)
# Show title counts by sex
table(full$Sex, full$Title)
-4
votes
1 answer
What does these Pandas code says ?, pls explain it to in normal term?
I wanna understand this code in a feature engineering term
train['TransactionAmt_to_mean_card1'] = train['TransactionAmt'] / train.groupby(['card1'])['TransactionAmt'].transform('mean')
Anubhav Sinha
- 150
- 2
- 16
-4
votes
1 answer
Feature Engineering Salary Data using Categorical Column as a condition
Need to convert salary amount to annualised salaries considering the Categorical Column :
'M' - monthly
'Y' - yearly
'W' - weekly
'B' - bi weekly
df = pd.DataFrame({'Name':['A','B','C','D','E'],
…
DEEPAK GIRDHAR
- 1
- 3