Every file the exercises ask for lives in the book's companion repository, github.com/jeong-yeol/AOR_with_AI. It is public, and nothing here needs a download. Copy the line under a file, paste it into a Colab cell, and pandas reads it straight from the web.
Each line below is complete on its own. Put
import pandas as pd in the cell above it and you are set.
Every file is synthetic. It was written for the book, and it is free to use, copy, and pass on for teaching and research.
The city the book runs on. Most lessons start here.
11,010 reviews of 200 restaurants, 2019 to 2022.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/maple_city_reviews.csv")The 200 restaurants, with cuisine, neighborhood, and coordinates.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/maple_city_businesses.csv")Small standalone sets. Each one is cut for a single chapter or exercise.
500 hotel reviews. This is the mini-project's data.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_hotel_reviews.csv")1,000 restaurant reviews.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_restaurant_reviews_1000.csv")A compact panel example.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_business_month_panel.csv")Reviews labeled with churn.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_churn_reviews.csv")The changepoint and review bombing demo. Book chapter 8.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_incident_reviews.csv")Reviews with coordinates.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/samples/sample_spatial_reviews.csv")Analysis-ready tables, one per method chapter. Start from these when you do not want to build the features out of the raw reviews again.
Per-review sentiment and aspect features. Book chapters 5 and 11.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/features_review.csv")The restaurant-month panel. Book chapter 6.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/panel_recomputed.csv")The panel with the program indicator, for difference in differences. Book chapter 7.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/ch7_panel.csv")Monthly volume and sentiment series. Book chapter 8.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/ch8_monthly.csv")Per-restaurant table with coordinates and features. Book chapter 9.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/ch9_business.csv")Construct scores for SEM. Book chapter 10.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/ch10_scores.csv")LDA based scores for the same constructs, for comparison. Book chapter 10.
pd.read_csv("https://raw.githubusercontent.com/jeong-yeol/AOR_with_AI/main/data/maple_city/derived/ch10_scores_lda.csv")The same repository carries seven Colab notebooks, one per stage of the book, and the Gemini prompt library the lessons work from.