wordcloud_dku.py

# -------------------------------------------------------------------------------- NOTEBOOK-CELL: CODE
# -*- coding: utf-8 -*-
import dataiku
import pandas as pd, numpy as np
import os

# Read recipe inputs
positive_python = dataiku.Dataset("positive_python")
df = positive_python.get_dataframe()
# Write recipe outputs
positive_python_folder = dataiku.Folder("positive_python_folder")
folder_path = positive_python_folder.get_path()

# -------------------------------------------------------------------------------- NOTEBOOK-CELL: CODE
# plotting libs
import wordcloud
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

# -------------------------------------------------------------------------------- NOTEBOOK-CELL: CODE
## wordcloud creation
wc = wordcloud.WordCloud(
        background_color='white',
        max_font_size=40,
        scale=3
).generate(str(df["tweet_simple"]))
fig = plt.figure()
plt.axis('off')
plt.imshow(wc)
plt.show()

# -------------------------------------------------------------------------------- NOTEBOOK-CELL: CODE
## save the wordcloud to the output folder
path_fig = folder_path + '/' + "wordcloud"
plt.savefig(path_fig)

# -------------------------------------------------------------------------------- NOTEBOOK-CELL: CODE
import dataiku.insights
id = "wordcloud_pos_python"
dataiku.insights.save_figure(id)