Last active
April 29, 2022 17:44
-
-
Save Finesim97/adf35b1d057dada6b93a3e3c40d57749 to your computer and use it in GitHub Desktop.
Helpful stuff dealing with transactional (bought stuff) in pandas
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from random import choices, choice | |
| import pandas as pd | |
| import numpy as np | |
| nrows=1000 | |
| customers = ["John", "Mary", "Alex", "Smith"] | |
| products = ["Beverage", "Meat", "Vegetable", "Fruit"] | |
| example_data = pd.DataFrame({"customer_id":choices(customers, k=nrows), "article_id":choices(products, k=nrows)}).astype("category") | |
| print(example_data.head()) | |
| # get most bought articles | |
| example = example_data.groupby(["customer_id", "article_id"], observed=True).size() | |
| print(example.head(3)) | |
| # convert it to a dataframe | |
| example=example.reset_index().rename(columns={0:"count"}) | |
| print(example.head(3)) | |
| example.sort_values(['customer_id', "count"],inplace=True, ascending=False) | |
| print(example.head(3)) | |
| # get two most bought | |
| example = example.groupby("customer_id", observed=True)["article_id"].apply(lambda x: x.head(2).to_list()) | |
| print(example.head(3)) | |
| # score predictions of a recommender systems (doesn't correctly deal with repeats) | |
| products = np.arange(10) | |
| maximum_actuals = np.arange(3)+1 | |
| truth = pd.DataFrame({"customer":customers, 'y':[choices(products, k=choice(maximum_actuals)) for _ in range(len(customers))]}) | |
| pred = pd.DataFrame({"customer":customers, 'y':[choices(products, k=len(maximum_actuals)) for _ in range(len(customers))]}) | |
| def recall(customertruth, customerpred): | |
| return sum([1 for pred in customerpred if pred in customertruth])/len(customertruth) | |
| def score(truth, pred, fun): | |
| combined = pd.merge(truth, pred, how="left", on="customer", suffixes=["_truth", "_pred"]) | |
| return combined.apply(lambda x:fun(customertruth=x['y_truth'], customerpred=x['y_pred']), axis=1) | |
| print(score(truth, truth, recall).mean()) | |
| print(score(truth, pred, recall).mean()) | |
| print("----") | |
| print(score(truth, pred, recall).iloc[0],truth.iloc[0,1],pred.iloc[0,1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment