#!/usr/bin/env python
# coding: utf-8

# In[ ]:


get_ipython().system('git clone https://github.com/gotec/git2net-tutorials')
import os
os.chdir('git2net-tutorials')
get_ipython().system('pip install -r requirements.txt')
os.chdir('..')
get_ipython().system('git clone https://github.com/gotec/git2net git2net4analysis')


# In[ ]:


import git2net
import os
import pandas as pd
import sqlite3
from collections import Counter


# # Author disambiguation
# 
# In the previous tutorial we discussed the options of `git2net`'s `mine_git_repo()` function.
# Let's now call this function with its default options and have a closer look at the results we get.

# In[ ]:


# We assume a clone of git2net's repository exists in the folder below following the first tutorial.
git_repo_dir = 'git2net4analysis'

# Here, we specify the database in which we will store the results of the mining process.
sqlite_db_file = 'git2net4analysis.db'

# Remove database if exists
if os.path.exists(sqlite_db_file):
    os.remove(sqlite_db_file)
    
git2net.mine_git_repo(git_repo_dir, sqlite_db_file)


# Specifically, we are interested in who worked on the project.
# Using the `commits` table in the resulting database, we can find this out.

# In[ ]:


with sqlite3.connect(sqlite_db_file) as con:
    authors = pd.read_sql("""SELECT author_name, author_email FROM commits""", con)

Counter(['{}, <{}>'.format(row.author_name, row.author_email) for idx, row in authors.iterrows()])


# The results show that both *Ingo Scholtes* and *Christoph Gote* made commits with multiple different name-email combinations, i.e., using multiple different aliases.
# Let's try to understand why this could be an issue based on an example from one of our [recent publications](https://arxiv.org/abs/2201.04588).
# In this project, we use `git2net` to study the relationship between team size and productivity using over 200 repositories from GitHub.
# If we used the identities above, we would overestimate the team size (assuming the team size is the number of name-email combinations).
# Simultaneously, we would underestimate the productivity of individual team members (assuming the productivity is the number of commits).
# As a consequence, we would potentially come to vastly different conclusions.
# Therefore, we need a method to disambiguate which aliases belong to the same author.
# 
# One might assume from the results above that we could simply use the names instead of name-email information.
# However, similar challenges can arise here too.
# Just think of middle names or apostrophes/umlauts, which might be stored differently on one computer compared to another.
# To deal with these challenges, `git2net` uses the Open Source name disambiguation tool `gambit` that we have developed specifically with the application in `git2net` in mind.
# We provide links to its [development repository](https://github.com/gotec/gambit) and the [original publication](https://arxiv.org/abs/2103.05666) for those of you who are interested.
# 
# Let's now apply `gambit` to the database from above and look at the results.
# To do so, we can simply call the function `disambiguate_aliases_db()` on the `sqlite_db_file` resulting from `mine_git_repo()`.

# In[ ]:


git2net.disambiguate_aliases_db(sqlite_db_file)

with sqlite3.connect(sqlite_db_file) as con:
    authors = pd.read_sql("""SELECT author_name, author_email, author_id FROM commits""", con)

Counter(['{} --- {}, <{}>'.format(row.author_id, row.author_name, row.author_email)
         for idx, row in authors.iterrows()])


# We find that&mdash;as we were hoping for&mdash;`gambit` assigns both aliases of Ingo Scholtes and Christoph Gote the same `author_id`s, respectively.
# Hence, we can use `author_id` in our subsequent analyses and visualisations as a unique identifier for the different authors active in the repository.

# With this, we conclude our tutorial on author disambiguation.
# We have now covered the cloning of repositories and the different options you can select during mining.
# Finally, we showed how to disambiguate author identities, providing clean data for our subsequent analyses.
# In the following tutorial, it is finally time to look at the `net`work part in `git2net`!