In [ ]:

! pip install transformers==4.15.0 sentence-transformers datasets

! pip install transformers==4.15.0 sentence-transformers datasets

Requirement already satisfied: transformers==4.15.0 in /usr/local/lib/python3.7/dist-packages (4.15.0)
Requirement already satisfied: sentence-transformers in /usr/local/lib/python3.7/dist-packages (2.2.0)
Requirement already satisfied: datasets in /usr/local/lib/python3.7/dist-packages (2.0.0)
Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (2.23.0)
Requirement already satisfied: tokenizers<0.11,>=0.10.1 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (0.10.3)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (6.0)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (1.21.5)
Requirement already satisfied: huggingface-hub<1.0,>=0.1.0 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (0.4.0)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (2019.12.20)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (21.3)
Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (4.11.3)
Requirement already satisfied: filelock in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (3.6.0)
Requirement already satisfied: sacremoses in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (0.0.49)
Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.7/dist-packages (from transformers==4.15.0) (4.63.0)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub<1.0,>=0.1.0->transformers==4.15.0) (3.10.0.2)
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->transformers==4.15.0) (3.0.7)
Requirement already satisfied: scipy in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (1.4.1)
Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (1.10.0+cu111)
Requirement already satisfied: nltk in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (3.2.5)
Requirement already satisfied: sentencepiece in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (0.1.96)
Requirement already satisfied: scikit-learn in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (1.0.2)
Requirement already satisfied: torchvision in /usr/local/lib/python3.7/dist-packages (from sentence-transformers) (0.11.1+cu111)
Requirement already satisfied: pandas in /usr/local/lib/python3.7/dist-packages (from datasets) (1.3.5)
Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.7/dist-packages (from datasets) (2022.3.0)
Requirement already satisfied: responses<0.19 in /usr/local/lib/python3.7/dist-packages (from datasets) (0.18.0)
Requirement already satisfied: multiprocess in /usr/local/lib/python3.7/dist-packages (from datasets) (0.70.12.2)
Requirement already satisfied: pyarrow>=5.0.0 in /usr/local/lib/python3.7/dist-packages (from datasets) (6.0.1)
Requirement already satisfied: dill in /usr/local/lib/python3.7/dist-packages (from datasets) (0.3.4)
Requirement already satisfied: aiohttp in /usr/local/lib/python3.7/dist-packages (from datasets) (3.8.1)
Requirement already satisfied: xxhash in /usr/local/lib/python3.7/dist-packages (from datasets) (3.0.0)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests->transformers==4.15.0) (2021.10.8)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests->transformers==4.15.0) (1.25.11)
Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->transformers==4.15.0) (2.10)
Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->transformers==4.15.0) (3.0.4)
Requirement already satisfied: asynctest==0.13.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (0.13.0)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (21.4.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (6.0.2)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (1.3.0)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (1.2.0)
Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (2.0.12)
Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (1.7.2)
Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.7/dist-packages (from aiohttp->datasets) (4.0.2)
Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata->transformers==4.15.0) (3.7.0)
Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from nltk->sentence-transformers) (1.15.0)
Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas->datasets) (2.8.2)
Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas->datasets) (2018.9)
Requirement already satisfied: click in /usr/local/lib/python3.7/dist-packages (from sacremoses->transformers==4.15.0) (7.1.2)
Requirement already satisfied: joblib in /usr/local/lib/python3.7/dist-packages (from sacremoses->transformers==4.15.0) (1.1.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn->sentence-transformers) (3.1.0)
Requirement already satisfied: pillow!=8.3.0,>=5.3.0 in /usr/local/lib/python3.7/dist-packages (from torchvision->sentence-transformers) (7.1.2)

In [ ]:

from datasets import load_dataset
data = load_dataset('emotion', split='train')

from datasets import load_dataset data = load_dataset('emotion', split='train')

Using custom data configuration default
Reusing dataset emotion (/root/.cache/huggingface/datasets/emotion/default/0.0.0/348f63ca8e27b3713b6c04d723efe6d824a56fb3d1449794716c0f0296072705)

In [ ]:

data["label"]

data["label"]

Out[ ]:

[0,
 0,
 3,
 2,
 3,
 0,
 5,
 4,
 1,
 2,
 0,
 1,
 3,
 0,
 1,
 1,
 0,
 0,
 0,
 4,
 3,
 4,
 1,
 1,
 3,
 0,
 0,
 0,
 3,
 1,
 1,
 4,
 5,
 3,
 1,
 1,
 1,
 1,
 3,
 1,
 1,
 1,
 1,
 1,
 0,
 0,
 1,
 2,
 1,
 3,
 1,
 0,
 3,
 4,
 1,
 0,
 0,
 5,
 1,
 1,
 1,
 2,
 4,
 4,
 5,
 3,
 3,
 0,
 2,
 1,
 0,
 0,
 1,
 0,
 0,
 0,
 1,
 1,
 1,
 3,
 0,
 3,
 3,
 3,
 1,
 1,
 1,
 1,
 0,
 4,
 2,
 3,
 0,
 3,
 2,
 0,
 1,
 1,
 0,
 3,
 2,
 1,
 1,
 1,
 0,
 1,
 1,
 1,
 1,
 0,
 1,
 1,
 2,
 0,
 0,
 1,
 1,
 0,
 1,
 1,
 4,
 4,
 4,
 0,
 2,
 1,
 1,
 2,
 4,
 5,
 1,
 1,
 1,
 1,
 3,
 4,
 1,
 3,
 2,
 3,
 0,
 1,
 0,
 3,
 1,
 5,
 0,
 3,
 3,
 0,
 1,
 4,
 1,
 1,
 4,
 0,
 5,
 5,
 1,
 3,
 4,
 3,
 0,
 3,
 0,
 4,
 0,
 1,
 5,
 4,
 1,
 3,
 1,
 3,
 1,
 4,
 4,
 0,
 1,
 1,
 0,
 5,
 1,
 4,
 1,
 0,
 1,
 1,
 1,
 4,
 1,
 5,
 1,
 3,
 0,
 0,
 1,
 3,
 0,
 1,
 1,
 5,
 1,
 4,
 1,
 4,
 0,
 4,
 2,
 0,
 4,
 2,
 0,
 0,
 3,
 1,
 2,
 3,
 0,
 5,
 3,
 1,
 0,
 3,
 1,
 1,
 1,
 1,
 1,
 0,
 1,
 2,
 1,
 0,
 3,
 5,
 1,
 3,
 1,
 2,
 0,
 0,
 1,
 0,
 0,
 1,
 0,
 1,
 1,
 1,
 4,
 0,
 3,
 0,
 3,
 2,
 1,
 2,
 0,
 1,
 1,
 1,
 0,
 1,
 0,
 3,
 2,
 0,
 2,
 0,
 0,
 0,
 0,
 0,
 0,
 4,
 1,
 0,
 0,
 1,
 2,
 0,
 3,
 0,
 2,
 1,
 1,
 1,
 0,
 1,
 0,
 1,
 1,
 1,
 0,
 0,
 0,
 2,
 4,
 0,
 4,
 1,
 1,
 4,
 1,
 3,
 3,
 2,
 0,
 5,
 1,
 3,
 0,
 0,
 3,
 2,
 5,
 0,
 2,
 1,
 3,
 1,
 0,
 0,
 1,
 1,
 4,
 0,
 3,
 1,
 2,
 1,
 1,
 1,
 1,
 1,
 2,
 1,
 4,
 4,
 1,
 1,
 3,
 1,
 1,
 1,
 0,
 5,
 1,
 1,
 0,
 5,
 1,
 4,
 1,
 3,
 2,
 3,
 4,
 5,
 1,
 3,
 0,
 0,
 0,
 4,
 1,
 4,
 1,
 3,
 0,
 2,
 3,
 0,
 2,
 2,
 1,
 0,
 1,
 1,
 3,
 1,
 2,
 1,
 1,
 0,
 5,
 1,
 1,
 0,
 5,
 3,
 1,
 1,
 2,
 1,
 2,
 2,
 1,
 0,
 1,
 0,
 4,
 3,
 0,
 3,
 1,
 4,
 5,
 2,
 0,
 0,
 1,
 5,
 2,
 0,
 0,
 1,
 4,
 1,
 1,
 1,
 2,
 4,
 0,
 0,
 4,
 2,
 1,
 0,
 1,
 0,
 1,
 0,
 1,
 0,
 1,
 1,
 3,
 0,
 4,
 0,
 0,
 3,
 5,
 5,
 1,
 5,
 4,
 2,
 3,
 1,
 4,
 0,
 3,
 0,
 1,
 4,
 1,
 1,
 1,
 1,
 5,
 3,
 0,
 1,
 0,
 3,
 2,
 0,
 2,
 3,
 2,
 2,
 1,
 1,
 0,
 1,
 0,
 1,
 3,
 1,
 4,
 0,
 1,
 0,
 5,
 1,
 1,
 2,
 1,
 0,
 3,
 1,
 0,
 0,
 0,
 1,
 1,
 1,
 0,
 0,
 3,
 3,
 1,
 0,
 5,
 1,
 1,
 0,
 3,
 1,
 3,
 1,
 1,
 2,
 3,
 1,
 1,
 1,
 1,
 1,
 1,
 1,
 4,
 1,
 4,
 0,
 3,
 3,
 0,
 2,
 0,
 0,
 0,
 5,
 4,
 0,
 0,
 1,
 4,
 1,
 0,
 0,
 3,
 0,
 3,
 3,
 2,
 1,
 1,
 0,
 1,
 1,
 1,
 2,
 2,
 2,
 1,
 5,
 4,
 0,
 3,
 0,
 4,
 1,
 3,
 1,
 1,
 0,
 1,
 4,
 1,
 3,
 0,
 3,
 1,
 2,
 2,
 0,
 4,
 0,
 0,
 0,
 4,
 0,
 3,
 1,
 1,
 0,
 4,
 4,
 3,
 3,
 0,
 0,
 3,
 3,
 1,
 4,
 0,
 0,
 4,
 1,
 4,
 0,
 0,
 1,
 0,
 3,
 0,
 2,
 5,
 1,
 1,
 1,
 1,
 1,
 0,
 0,
 2,
 4,
 3,
 1,
 2,
 1,
 1,
 4,
 3,
 4,
 0,
 3,
 3,
 3,
 4,
 1,
 2,
 3,
 4,
 3,
 1,
 4,
 0,
 0,
 3,
 1,
 3,
 4,
 4,
 5,
 0,
 1,
 1,
 1,
 2,
 0,
 1,
 0,
 3,
 1,
 1,
 4,
 4,
 1,
 4,
 3,
 3,
 3,
 1,
 0,
 1,
 1,
 1,
 3,
 4,
 3,
 1,
 0,
 1,
 4,
 1,
 0,
 3,
 0,
 0,
 1,
 1,
 0,
 2,
 1,
 0,
 3,
 2,
 0,
 1,
 1,
 4,
 3,
 1,
 1,
 2,
 5,
 4,
 4,
 3,
 3,
 2,
 0,
 0,
 1,
 2,
 3,
 1,
 3,
 1,
 1,
 1,
 4,
 4,
 2,
 0,
 2,
 1,
 1,
 0,
 0,
 3,
 3,
 3,
 3,
 0,
 1,
 0,
 1,
 4,
 0,
 1,
 0,
 1,
 5,
 4,
 1,
 1,
 4,
 4,
 0,
 0,
 3,
 0,
 2,
 1,
 5,
 1,
 5,
 1,
 4,
 1,
 1,
 1,
 1,
 5,
 2,
 0,
 2,
 1,
 0,
 1,
 1,
 0,
 1,
 1,
 1,
 1,
 4,
 4,
 4,
 4,
 3,
 2,
 0,
 1,
 1,
 0,
 0,
 0,
 0,
 1,
 0,
 0,
 4,
 1,
 3,
 1,
 1,
 4,
 3,
 1,
 3,
 3,
 3,
 3,
 3,
 1,
 4,
 0,
 2,
 0,
 4,
 2,
 1,
 5,
 1,
 1,
 1,
 1,
 0,
 5,
 1,
 3,
 3,
 3,
 1,
 1,
 0,
 2,
 0,
 1,
 3,
 3,
 3,
 4,
 1,
 1,
 4,
 0,
 5,
 1,
 2,
 0,
 1,
 1,
 0,
 0,
 0,
 3,
 1,
 0,
 0,
 0,
 0,
 1,
 5,
 1,
 3,
 2,
 1,
 3,
 0,
 1,
 3,
 0,
 4,
 4,
 0,
 0,
 4,
 0,
 2,
 4,
 1,
 1,
 4,
 1,
 3,
 1,
 1,
 3,
 1,
 1,
 2,
 3,
 1,
 1,
 1,
 3,
 1,
 2,
 4,
 3,
 2,
 0,
 4,
 0,
 0,
 2,
 1,
 4,
 2,
 1,
 1,
 0,
 1,
 0,
 4,
 1,
 0,
 2,
 0,
 2,
 0,
 0,
 3,
 2,
 3,
 1,
 3,
 0,
 0,
 1,
 1,
 3,
 0,
 5,
 1,
 2,
 0,
 3,
 4,
 2,
 1,
 1,
 3,
 1,
 0,
 1,
 1,
 1,
 2,
 1,
 0,
 2,
 4,
 0,
 1,
 0,
 3,
 1,
 1,
 0,
 1,
 2,
 1,
 1,
 1,
 3,
 4,
 0,
 1,
 0,
 0,
 2,
 3,
 1,
 2,
 0,
 1,
 4,
 0,
 1,
 1,
 0,
 0,
 2,
 1,
 0,
 0,
 0,
 0,
 3,
 0,
 1,
 0,
 1,
 0,
 2,
 3,
 1,
 4,
 0,
 0,
 1,
 1,
 3,
 4,
 2,
 1,
 0,
 3,
 0,
 1,
 ...]

In [ ]:

data.set_format("pandas")

data.set_format("pandas")

In [ ]:

df = data[:]
df.head()

df = data[:] df.head()

Out[ ]:

	text	label
0	i didnt feel humiliated	0
1	i can go from feeling so hopeless to so damned...	0
2	im grabbing a minute to post i feel greedy wrong	3
3	i am ever feeling nostalgic about the fireplac...	2
4	i am feeling grouchy	3

Sentence Transformer Embeddings¶

In [ ]:

import pandas as pd
from sentence_transformers import SentenceTransformer
from tqdm import tqdm
import numpy as np

import pandas as pd from sentence_transformers import SentenceTransformer from tqdm import tqdm import numpy as np

In [ ]:

def embedding_generator(df_path, model):
  tqdm.pandas()
  model = SentenceTransformer(model)
  df['Embeddings'] = df['text'].progress_apply(lambda x: model.encode(x))
  return df

def embedding_generator(df_path, model): tqdm.pandas() model = SentenceTransformer(model) df['Embeddings'] = df['text'].progress_apply(lambda x: model.encode(x)) return df

In [ ]:

def inputgen(df):
  a = []
  for i in tqdm(range(len(df))):
    a.append(np.array(df["Embeddings"][i]))
  a = np.array(a)
  print(a.shape)
  return a

def inputgen(df): a = [] for i in tqdm(range(len(df))): a.append(np.array(df["Embeddings"][i])) a = np.array(a) print(a.shape) return a

In [ ]:

df = df[0:2000]

df = df[0:2000]

In [ ]:

model1 = "sentence-transformers/all-MiniLM-L6-v2" 
inputgen_input = embedding_generator(df, model1)
print("Model 1 embedding completed")
embed_output = inputgen(inputgen_input)
print("Model 1 array completed")

model1 = "sentence-transformers/all-MiniLM-L6-v2" inputgen_input = embedding_generator(df, model1) print("Model 1 embedding completed") embed_output = inputgen(inputgen_input) print("Model 1 array completed")

100%|██████████| 2000/2000 [00:13<00:00, 149.65it/s]

Model 1 embedding completed

100%|██████████| 2000/2000 [00:00<00:00, 69706.98it/s]

(2000, 384)
Model 1 array completed

In [ ]:

embed = pd.DataFrame(embed_output)
df = pd.concat([df, embed], axis=1)
df

embed = pd.DataFrame(embed_output) df = pd.concat([df, embed], axis=1) df

Out[ ]:

	text	label	Embeddings	0	1	2	3	4	5	6	...	374	375	376	377	378	379	380	381	382	383
0	i didnt feel humiliated	0	[-0.055050932, -0.007696963, 0.06353026, -0.03...	-0.055051	-0.007697	0.063530	-0.039664	0.116901	-0.123296	0.058080	...	0.063319	-0.044138	-0.034640	0.021249	-0.029084	0.084679	0.016152	0.015425	-0.135161	-0.064534
1	i can go from feeling so hopeless to so damned...	0	[0.009238882, -0.05296433, 0.01926256, 0.03402...	0.009239	-0.052964	0.019263	0.034021	0.125202	0.027428	0.077058	...	-0.016320	-0.024402	-0.044897	0.132352	-0.082222	0.003469	0.095559	-0.060182	-0.027176	-0.026275
2	im grabbing a minute to post i feel greedy wrong	3	[-0.074502885, -0.010641884, -0.0034595674, -0...	-0.074503	-0.010642	-0.003460	-0.073246	-0.018509	-0.026024	0.023559	...	0.050347	-0.030673	-0.001018	0.019752	0.078385	-0.010269	0.041514	-0.024779	-0.042020	0.024512
3	i am ever feeling nostalgic about the fireplac...	2	[0.10859442, 0.09532223, 0.03647684, 0.0151784...	0.108594	0.095322	0.036477	0.015178	0.089073	-0.012647	-0.089686	...	0.019334	-0.076964	-0.004122	0.023587	0.056529	0.024166	0.103731	-0.044091	-0.109329	0.034851
4	i am feeling grouchy	3	[-0.016712204, -0.07877089, 0.032170087, -0.05...	-0.016712	-0.078771	0.032170	-0.053829	0.115593	-0.051190	0.132093	...	-0.011990	0.003192	-0.077645	-0.016146	0.007182	0.029738	0.059137	-0.062703	-0.019559	-0.057704
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1995	i feel so low and i havent felt this low in a ...	0	[0.00746265, -0.072956935, 0.06638428, 0.05247...	0.007463	-0.072957	0.066384	0.052478	0.011782	-0.002765	0.015952	...	-0.046977	-0.010428	-0.048182	0.081015	-0.056379	-0.043684	0.059703	-0.061770	-0.076507	-0.000722
1996	i absolutely love this skinny fiber it is doin...	1	[-0.05117633, -0.04654245, 0.042185836, 0.0601...	-0.051176	-0.046542	0.042186	0.060135	0.005652	-0.068989	0.031247	...	-0.010567	-0.019804	-0.038921	0.050018	-0.011048	0.008017	0.041045	-0.010521	0.005083	-0.002920
1997	i feel as if im in some strange catholic vortex	5	[0.0092844125, -0.094246, 0.026456287, -0.0027...	0.009284	-0.094246	0.026456	-0.002791	0.047796	-0.070760	0.011053	...	0.087301	-0.005810	0.040688	0.020890	-0.022804	-0.063676	0.061230	-0.020718	-0.048927	-0.092958
1998	i have a feeling that many of you will be surp...	5	[0.11245156, -0.03292613, 0.11352201, -0.03423...	0.112452	-0.032926	0.113522	-0.034240	0.062835	0.008078	0.031408	...	0.096730	0.014149	-0.011893	0.077310	-0.106346	0.016515	0.078990	0.053615	-0.086291	-0.006568
1999	i am so connected with families that are not m...	1	[-0.03639206, -0.10061437, -0.0018109059, 0.02...	-0.036392	-0.100614	-0.001811	0.025786	-0.028809	-0.010301	0.012143	...	0.034679	-0.006586	0.019008	0.090166	0.052975	0.014769	0.087924	0.023971	-0.021222	-0.063778

2000 rows × 387 columns

Embeddings Dimensionality Reduction¶

In [ ]:

! pip install umap-learn

! pip install umap-learn

Requirement already satisfied: umap-learn in /usr/local/lib/python3.7/dist-packages (0.5.2)
Requirement already satisfied: scipy>=1.0 in /usr/local/lib/python3.7/dist-packages (from umap-learn) (1.4.1)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.7/dist-packages (from umap-learn) (1.21.5)
Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from umap-learn) (4.63.0)
Requirement already satisfied: numba>=0.49 in /usr/local/lib/python3.7/dist-packages (from umap-learn) (0.51.2)
Requirement already satisfied: scikit-learn>=0.22 in /usr/local/lib/python3.7/dist-packages (from umap-learn) (1.0.2)
Requirement already satisfied: pynndescent>=0.5 in /usr/local/lib/python3.7/dist-packages (from umap-learn) (0.5.6)
Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from numba>=0.49->umap-learn) (57.4.0)
Requirement already satisfied: llvmlite<0.35,>=0.34.0.dev0 in /usr/local/lib/python3.7/dist-packages (from numba>=0.49->umap-learn) (0.34.0)
Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from pynndescent>=0.5->umap-learn) (1.1.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.22->umap-learn) (3.1.0)

In [ ]:

from umap import UMAP
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
import pandas as pd
from sentence_transformers import SentenceTransformer
from tqdm import tqdm
import numpy as np

from umap import UMAP import pandas as pd from sklearn.preprocessing import MinMaxScaler import pandas as pd from sentence_transformers import SentenceTransformer from tqdm import tqdm import numpy as np

In [ ]:

def embedding_generator(df_path, model):
  tqdm.pandas()
  model = SentenceTransformer(model)
  df['Embeddings'] = df['text'].progress_apply(lambda x: model.encode(x))
  return df

def embedding_generator(df_path, model): tqdm.pandas() model = SentenceTransformer(model) df['Embeddings'] = df['text'].progress_apply(lambda x: model.encode(x)) return df

In [ ]:

def inputgen(df):
  a = []
  for i in tqdm(range(len(df))):
    a.append(np.array(df["Embeddings"][i]))
  a = np.array(a)
  print(a.shape)
  return a

def inputgen(df): a = [] for i in tqdm(range(len(df))): a.append(np.array(df["Embeddings"][i])) a = np.array(a) print(a.shape) return a

In [ ]:

def dimensionality_reduction(embed_arr, label):
  X_scaled = MinMaxScaler().fit_transform(embed_arr)
  mapper = UMAP(n_components=2, metric="cosine").fit(X_scaled)
  df_emb = pd.DataFrame(mapper.embedding_, columns=["X", "Y"])
  df_emb["label"] = label
  print(df_emb)
  return df_emb

def dimensionality_reduction(embed_arr, label): X_scaled = MinMaxScaler().fit_transform(embed_arr) mapper = UMAP(n_components=2, metric="cosine").fit(X_scaled) df_emb = pd.DataFrame(mapper.embedding_, columns=["X", "Y"]) df_emb["label"] = label print(df_emb) return df_emb

In [ ]:

model1 = "sentence-transformers/all-MiniLM-L6-v2" 
inputgen_input = embedding_generator(df, model1)
print("Embedding completed")
embed_output = inputgen(inputgen_input)
print("Array completed")
dim_emb_out = dimensionality_reduction(embed_output, df["label"])
print("UMAP completed")

model1 = "sentence-transformers/all-MiniLM-L6-v2" inputgen_input = embedding_generator(df, model1) print("Embedding completed") embed_output = inputgen(inputgen_input) print("Array completed") dim_emb_out = dimensionality_reduction(embed_output, df["label"]) print("UMAP completed")

100%|██████████| 2000/2000 [00:14<00:00, 137.54it/s]

Embedding completed

100%|██████████| 2000/2000 [00:00<00:00, 71517.18it/s]

(2000, 384)
Array completed
             X          Y  label
0     4.410917  10.360144      0
1     7.095046  11.037721      0
2     6.351001   9.905983      3
3     8.679171   9.845695      2
4     5.573699  12.767012      3
...        ...        ...    ...
1995  6.500954  11.825342      0
1996  9.314243  11.284079      1
1997  6.900813   9.577901      5
1998  8.642849   9.790328      5
1999  7.501454   8.454765      1

[2000 rows x 3 columns]
UMAP completed

In [ ]:

dim_emb_out

dim_emb_out

Out[ ]:

	X	Y	label
0	4.410917	10.360144	0
1	7.095046	11.037721	0
2	6.351001	9.905983	3
3	8.679171	9.845695	2
4	5.573699	12.767012	3
...	...	...	...
1995	6.500954	11.825342	0
1996	9.314243	11.284079	1
1997	6.900813	9.577901	5
1998	8.642849	9.790328	5
1999	7.501454	8.454765	1

2000 rows × 3 columns

Visualization of Embeddings¶

In [ ]:

import matplotlib.pyplot as plt

import matplotlib.pyplot as plt

In [ ]:

fig, axes = plt.subplots(2, 3, figsize=(7,5))
axes = axes.flatten()
cmaps = ["Greys", "Blues", "Oranges", "Reds", "Purples", "Greens"]
labels =df["label"].unique()
for i, (label, cmap) in enumerate(zip(labels, cmaps)):
    df_emb_sub = dim_emb_out.query(f"label == {i}")
    print(df_emb_sub)
    axes[i].hexbin(df_emb_sub["X"], df_emb_sub["Y"], cmap=cmap,
                   gridsize=10, linewidths=(0,))
    axes[i].set_title(label)
    axes[i].set_xticks([]), axes[i].set_yticks([])

plt.tight_layout()
plt.show()

fig, axes = plt.subplots(2, 3, figsize=(7,5)) axes = axes.flatten() cmaps = ["Greys", "Blues", "Oranges", "Reds", "Purples", "Greens"] labels =df["label"].unique() for i, (label, cmap) in enumerate(zip(labels, cmaps)): df_emb_sub = dim_emb_out.query(f"label == {i}") print(df_emb_sub) axes[i].hexbin(df_emb_sub["X"], df_emb_sub["Y"], cmap=cmap, gridsize=10, linewidths=(0,)) axes[i].set_title(label) axes[i].set_xticks([]), axes[i].set_yticks([]) plt.tight_layout() plt.show()

             X          Y  label
0     4.410917  10.360144      0
1     7.095046  11.037721      0
5     6.884747  12.149796      0
10    5.573589  10.928417      0
13    7.363647  12.668382      0
...        ...        ...    ...
1983  7.338718   7.762202      0
1987  6.602554   9.052503      0
1989  6.382240  10.995190      0
1992  7.367487  11.797047      0
1995  6.500954  11.825342      0

[544 rows x 3 columns]
             X          Y  label
8     7.892040  10.033929      1
11    7.005034   9.483533      1
14    9.480061   8.485753      1
15    6.398749  12.128724      1
22    6.625608   7.409938      1
...        ...        ...    ...
1988  8.608582  11.570669      1
1991  9.189944   9.329336      1
1993  6.085050   9.369851      1
1996  9.314243  11.284079      1
1999  7.501454   8.454765      1

[702 rows x 3 columns]
             X          Y  label
3     8.679171   9.845695      2
9     5.858622   8.135866      2
47    7.230072   8.507003      2
61    5.531404  12.353902      2
68    6.735010   9.334861      2
...        ...        ...    ...
1972  5.786281  10.251306      2
1973  8.701107   9.829437      2
1978  4.189478   8.249639      2
1984  7.403680   9.066971      2
1985  5.714351  12.618199      2

[173 rows x 3 columns]
             X          Y  label
2     6.351001   9.905983      3
4     5.573699  12.767012      3
12    8.151361  10.702692      3
20    4.643733   9.135000      3
24    7.602103  12.617702      3
...        ...        ...    ...
1942  4.633220  11.428572      3
1946  8.804513  12.250484      3
1953  4.024027  10.380529      3
1963  9.191159  11.068044      3
1986  4.087564  11.096752      3

[268 rows x 3 columns]
             X          Y  label
7     5.388288   9.851950      4
19    6.385650  10.144875      4
21    8.048517  11.486029      4
31    6.078864  11.757133      4
53    8.348764   8.977859      4
...        ...        ...    ...
1955  7.125514   7.996155      4
1965  7.390118   9.450252      4
1975  4.810911   9.063455      4
1990  5.460900  11.757572      4
1994  7.669730  12.339661      4

[236 rows x 3 columns]
             X          Y  label
6     6.616123  13.090185      5
32    8.302124  10.460528      5
57    7.081882   8.609643      5
64    7.512016  12.824598      5
129   7.710279   7.798317      5
...        ...        ...    ...
1928  5.311825   7.922052      5
1945  7.558575   7.223899      5
1954  7.007526  11.439436      5
1997  6.900813   9.577901      5
1998  8.642849   9.790328      5

[77 rows x 3 columns]

In [ ]: