Created
May 28, 2020 02:37
-
-
Save TiGaI/94ff89c6d8bbdffe4f67b9666c657fa0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import plotly | |
import plotly.graph_objs as go | |
import pandas as pd | |
import numpy as np | |
import json | |
import nltk | |
#for NLP purpose | |
from nltk.corpus import stopwords | |
nltk.download('stopwords') | |
def create_plot(client): | |
query = """ | |
SELECT * | |
FROM tweetScraper.tweet | |
""" | |
df = client.query(query).to_dataframe() | |
stop = stopwords.words('english') | |
#convert to lower | |
df['newTweet'] = df['tweet'].apply(lambda x: ' '.join([word for word in x.lower().split() if word not in (stop)])) | |
#Remove Punctuations | |
df['newTweetRemove'] = df['newTweet'].str.replace('[^\w\s]','') | |
#Count Words | |
countFreq = df.newTweetRemove.str.split(expand=True).stack().value_counts()[:100] | |
bar = [go.Bar( | |
x=countFreq.index, | |
y=countFreq.values, | |
marker_color='lightsalmon', | |
text=countFreq.values, | |
textposition='auto' | |
) | |
] | |
graph = go.Figure(bar) | |
graph.update_layout( | |
title='Frequency Tweet Count', | |
xaxis_tickfont_size=14, | |
yaxis=dict( | |
title='Word Frequency Count', | |
titlefont_size=16, | |
tickfont_size=14, | |
), | |
legend=dict( | |
x=0, | |
y=1.0, | |
bgcolor='rgba(255, 255, 255, 0)', | |
bordercolor='rgba(255, 255, 255, 0)' | |
), | |
barmode='group', | |
xaxis_tickangle=-45, | |
bargap=0.15, # gap between bars of adjacent location coordinates. | |
bargroupgap=0.1 # gap between bars of the same location coordinate. | |
) | |
# Create a trace | |
table = go.Figure([go.Table( | |
header=dict( | |
values=df.columns[1:6], | |
font=dict(size=12), | |
align="left" | |
), | |
cells=dict( | |
values=[df[k].tolist() for k in df.columns[1:6]], | |
align = "left") | |
) | |
]) | |
table.update_layout( | |
autosize=True, | |
) | |
graphJSON = json.dumps(graph, cls=plotly.utils.PlotlyJSONEncoder) | |
tableJSON = json.dumps(table, cls=plotly.utils.PlotlyJSONEncoder) | |
return graphJSON, tableJSON |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment