alteryx / predict-customer-churn Goto Github PK

In the notebook under the "Interesting Values" section, you're using "is_cancel" as a feature. Doesn't that create a bias since you're providing future information to the model telling it that the customer has cancelled the subscription?

For example, my client table has more than one time_index I would like to use as a feature. Account open date, and last activity date.

After running the jupyter notebook "3. Feature Engineering.ipynb" in the update-reqs, I get two errors:

(1) in chunk [39]:
ValueError: ('Unknown transform primitive weekend. ', 'Call ft.primitives.list_primitives() to get', ' a list of available primitives') ,
I think this is because you specify transformation primitives as trans_primitives = ['weekend', 'cum_sum', 'day', 'month', 'diff', 'time_since_previous'], but 'weedend' is not a primitive, 'is_weekend' is a primitive.

(2) in chunk [42]:
'AttributeError: Cutoff time DataFrame must contain a column with either the same name as the target entity time_index or a column named "time" ',
I have check the dataframe of cutoff_time and members, they have the common columns "msno", so I have no idea about this issue?

I have a dataframe of person information that includes each person's quality of health (from 0 to 100)

e.g. if I extract just the Name and HealthQuality columns:

John: 70
Mary: 20
Paul: 40

etc etc.

After applying featuretools I noticed a new DIFF(HealthQuality) variable.
Difference between what exactly?

According to the docs, this is what DIFF does:

"Compute the difference between the value in a list and the previous value in that list."

Is featuretools calculating the difference between Mary and John's health quality in this instance?

I was running the program (3. Feature Engineering.ipynb) in the colab. The program can not go through by some reasons. It gave :"tuple is not allowed for map key". Can you help me to solve it? Thanks.

Hi, I was trying out the code in "2. Prediction Engineering.ipynb", particularly the "label_customer()" with a dataset that I have and in it I have several customers who only have a single transaction. Now for example if they registered for the service on 10th Jan and the membership expired on 15th Feb the code labels it as a false churn since there is no next transaction date. Is this a bug?

Is it possible to replicate the notebook code from step 3. I don't see the cutoff dates csv in kaggle? Do you know where it is?
https://github.com/Featuretools/predict-customer-churn/blob/main/churn/3.%20Feature%20Engineering.ipynb

(This link was in notebook 2)

https://www.kaggle.com/c/kkbox-churn-prediction-challenge/data?select=user_logs_v2.csv.7z

Hi,
i looking for the file sample_submission_v2.csv. should i build from Train....csv with pandas test_train_split from Pandas.

I notice that the links for notebooks in README are not correct

Firstly, thanks for the detailed notebooks! Learnt a lot from it.

In https://github.com/Featuretools/predict-customer-churn/blob/main/churn/3.%20Feature%20Engineering.ipynb,
I assume that the features num_25, num_50, num_75, num_985, num_100, and num_unq, etc represent the number of specific types of transactions (e.g., number of songs played with 25% completion, 50% completion, etc.) for each customer.

Wouldnt using these features (and various transformations/aggregations on it) in the windows lead to data leakage?

Because basically we are using the information from the future or outside the given time window to create features or train a model.

I have a similar use-case where we have few customer columns like ltv, nr_orders etc which reflect value "as of today". I am not sure how to handle these in the windows that are created.