In [6]:
!wget https://setup.johnsnowlabs.com/nlu/kaggle.sh -O - | bash
! pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple peanut_butter_data_time==3.0.1rc63 > /dev/null
# https://setup.johnsnowlabs.com/nlu/kaggle.sh
import nlu
--2021-05-04 05:52:22-- https://raw.githubusercontent.com/JohnSnowLabs/nlu/3.0.1rc1/scripts/kaggle_setup.sh
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1567 (1.5K) [text/plain]
Saving to: ‘STDOUT’
- 0%[ ] 0 --.-KB/s setup Kaggle for PySpark 3.0.2 and Spark NLP 3.0.2
- 100%[===================>] 1.53K --.-KB/s in 0.001s
2021-05-04 05:52:22 (2.51 MB/s) - written to stdout [1567/1567]
E: Failed to fetch http://security.ubuntu.com/ubuntu/pool/universe/o/openjdk-8/openjdk-8-jre-headless_8u252-b09-1~18.04_amd64.deb 404 Not Found [IP: 91.189.88.152 80]
E: Failed to fetch http://security.ubuntu.com/ubuntu/pool/universe/o/openjdk-8/openjdk-8-jdk-headless_8u252-b09-1~18.04_amd64.deb 404 Not Found [IP: 91.189.88.152 80]
E: Unable to fetch some archives, maybe run apt-get update or try with --fix-missing?
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
100 210M 100 210M 0 0 15.2M 0 0:00:13 0:00:13 --:--:-- 17.4M
WARNING: You are using pip version 20.1.1; however, version 21.1.1 is available.
You should consider upgrading via the '/opt/conda/bin/python3.7 -m pip install --upgrade pip' command.
WARNING: You are using pip version 20.1.1; however, version 21.1.1 is available.
You should consider upgrading via the '/opt/conda/bin/python3.7 -m pip install --upgrade pip' command.
In [7]:
import os
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
df = pd.read_csv("/kaggle/input/covid19-tweets/covid19_tweets.csv").iloc[0:10000]
In [8]:
import nlu
emotion_predictions = nlu.load('emotion').predict(df, output_level='document')
emotion_predictions['emotion'].value_counts().plot.bar(title='Predicted emotion label count in dataset')
classifierdl_use_emotion download started this may take some time. Approximate size to download 21.3 MB [OK!] tfhub_use download started this may take some time. Approximate size to download 923.7 MB [OK!] sentence_detector_dl download started this may take some time. Approximate size to download 354.6 KB [OK!]
Out[8]:
<matplotlib.axes._subplots.AxesSubplot at 0x7feabebad110>
In [9]:
counts = emotion_predictions.groupby(['source'])['emotion'].value_counts()
counts[counts > 100].plot.bar(figsize=(20,8), title= 'Emotion tweet counts grouped by tweet device source')
Out[9]:
<matplotlib.axes._subplots.AxesSubplot at 0x7fea9d78e8d0>
In [10]:
counts = emotion_predictions.groupby(['user_location'])['emotion'].value_counts()
counts[counts > 25].plot.bar(figsize=(20,6), title= 'Emotion tweet counts grouped by user location')
Out[10]:
<matplotlib.axes._subplots.AxesSubplot at 0x7feaa02f1ed0>
In [ ]: