Thomas added snippets and dense vectors

%% Cell type:code id:a144fa2a-d7a5-4c29-9223-bc17d8a09f42 tags:

``` python

import numpy as np

import pandas as pd

from tqdm import tqdm

import geopandas as gpd

import matplotlib.pyplot as plt

import networkx as nx

```

%% Cell type:markdown id:46a6719b-5757-4068-8f6b-b185a4595de2 tags:

## Reformatting cluster labels

Currently, the output of the clustering algorithm is a dataframe with columns plan_index, district, row_index, population, cluster_label.

For more efficient storage, we prefer a shorter dataframe with just plan_index, district, cluster_label.

%% Cell type:code id:73993582-f1a7-4daa-b3f8-f9d1920bd4f4 tags:

``` python

num_clusters = 30

input_filename = 'data/processed/centroids/ensemble_with_cluster_labels_k30.csv'

output_filename = 'cluster_labels_k30.csv'

```

%% Cell type:code id:5a03e2da-f6ee-425a-b396-b56c3d9a3685 tags:

``` python

df = pd.read_csv(input_filename) #load input file

```

%% Cell type:code id:28d0ff7d-f02c-4937-af6c-3f0264dffdeb tags:

``` python

newdf = df.groupby(by=['plan_index', 'district']).max() #group by plan_index and district and retain cluster label

```

%% Cell type:code id:4a154a8f-7580-40d7-a93b-35a13a0c0220 tags:

``` python

newdf[['cluster_label']].to_csv(output_filename) #output cluster label information to output file

```