Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
l_t = Most_Positive_text
w1_dict = dict()
for word in l_t.split():
w= word.strip()
if w in STOPWORDS:
continue
else:
w1_dict[w] = w1_dict.get(w,0)+1
w1_dict = {k: v for k, v in sorted(w1_dict.items(), key=lambda item: item[1],reverse=True)}
l_t = Most_Negative_text
w2_dict = dict()
for word in l_t.split():
w= word.strip()
if w in STOPWORDS:
continue
else:
w2_dict[w] = w2_dict.get(w,0)+1
w2_dict = {k: v for k, v in sorted(w2_dict.items(), key=lambda item: item[1],reverse=True)}
top_10_pos = list(w1_dict.keys())[:10]
top_10_neg = list(w2_dict.keys())[:10]
plt.subplot(1,2,1)
w_c = WordCloud(width=600,height=400,collocations = False,colormap='nipy_spectral').generate(' '.join(top_10_pos))
plt.title('Top 10 Words In Most Positive Tweets',fontsize=19,fontweight='bold')
plt.imshow(w_c)
plt.axis('off')
plt.subplot(1,2,2)
w_c = WordCloud(width=600,height=400,collocations = False,colormap='nipy_spectral').generate(' '.join(top_10_neg))
plt.title('Top 10 Words In Most Negative Tweets',fontsize=19,fontweight='bold')
plt.imshow(w_c)
plt.axis('off')
plt.show()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment