Created
September 12, 2020 00:55
-
-
Save foohm71/9a6426358cd7ce34503743d7a5ae68a2 to your computer and use it in GitHub Desktop.
Common functions
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
def make_autopct(values): | |
def my_autopct(pct): | |
total = sum(values) | |
val = int(round(pct*total/100.0)) | |
return '{p:.1f}% ({v:d})'.format(p=pct,v=val) | |
return my_autopct | |
def plotPieChart(column): | |
freq_count = Counter(df[column]) | |
fig, ax = plt.subplots(figsize=(15, 7), subplot_kw=dict(aspect="equal")) | |
patches, texts, autotexts = ax.pie(freq_count.values(), labels=freq_count.keys(), autopct=make_autopct(freq_count.values()), textprops=dict(color="w", size=12, weight='bold')) | |
ax.legend(patches, freq_count.keys(), loc="upper left") | |
ax.set_title(column) | |
plt.show() | |
def plotHorzBar(column): | |
data = df[column] | |
count = {} | |
for d in data: | |
words = d.split(";") | |
for w in words: | |
if w in count.keys(): | |
count[w] = count[w] + 1 | |
else: | |
count[w] = 1 | |
y_pos = np.arange(len(count.keys())) | |
plt.barh(y_pos,count.values()) | |
plt.yticks(y_pos, count.keys()) | |
plt.show() | |
def plotBar(column): | |
data = df[column] | |
data = data.dropna() | |
count = {1:0,2:0,3:0,4:0,5:0} | |
for d in data: | |
count[d] = count[d] + 1 | |
y_pos = range(1,6) | |
plt.bar(y_pos,count.values()) | |
plt.yticks(y_pos, count.keys()) | |
plt.title("1 - highly disagree, 5 - highly agree") | |
plt.show() | |
def plotWordCloud(column): | |
data = df[column] | |
data = data.dropna() | |
text = data.to_string() | |
wordcloud = WordCloud(width = 900, height = 500, random_state=1, background_color='salmon', colormap='Pastel1', collocations=False, stopwords = STOPWORDS).generate(text) | |
plt.figure(figsize=(20, 15)) | |
# Display image | |
plt.imshow(wordcloud) | |
# No axis details | |
plt.axis("off"); | |
def summarizeFeedback(column): | |
data = df[column] | |
data = data.dropna() | |
text = data.to_string() | |
summ_per = summarize(text, ratio = 0.30) | |
summ = Markdown('<h3>{}</h3>'.format(summ_per)) | |
return summ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment