Padhma

from wordcloud import WordCloud, STOPWORDS
from PIL import Image

# create a string with all the topic tags
github_tags = (" ").join(all_tags)

# assign the mask image to a variable
git_mask = np.array(Image.open('../input/wordcloud-mask/github_icon.jpg'))

# instantiate a word cloud object

Padhma

# length of tags list in each column
len_tags = [len(tag) for tag in topic_tags]

# create a new column -> total_tags
github_df['Total_Tags'] = len_tags

# group based on topic and calculate total_tags in each topic
topic_wise_tags = github_df.groupby('Topic').sum()['Total_Tags'].reset_index(name='Total Tags')

# set figure size and dpi

Padhma

import ast
from collections import Counter
# convert column to list of lists
topic_tags = github_df['Topic_Tags'].apply(lambda x: ast.literal_eval(x)).tolist()
# split all lists and select individual items
all_tags = [tag for topic in topic_tags for tag in topic]
# count the occurrence of each tag
tags_dict = Counter(all_tags)
# create a dataframe with most tags
toptags_df = pd.DataFrame(tags_dict.most_common(15), columns=['Name of the Tag','Count'])

Padhma

# create a dataframe using users_with_more_repos list
more_repos_users_df = github_df[github_df['User_Name'].isin(users_with_more_repos)][['Issues','Pull_Requests','Commits','Contributors']]

# set figure size and dpi
fig, ax = plt.subplots(figsize=(6,4), dpi=100)

# plot the correlation in a heatmap
sns.heatmap(more_repos_users_df.corr(), linewidths=0.1, vmax=1.0, square=True, linecolor='white', annot=True, cmap='summer');
fig.suptitle('Correlation of contributions among users with more repositories',fontsize=16, color = '#333F4B');

Padhma

popular_df = github_df.nlargest(n=100,columns=['Star'])[['Issues','Pull_Requests','Commits','Contributors']]

# set figure size and dpi
fig, ax = plt.subplots(figsize=(6,4), dpi=100)

# plot the correlation in a heatmap
sns.heatmap(popular_df.corr(), linewidths=0.1, vmax=1.0, square=True, linecolor='white', annot=True, cmap='summer');
fig.suptitle('Correlation of contributions in Top 100 popular repositories',fontsize=16, color = '#333F4B');

Padhma

# drop rows with any null values and create a dataframe with only the contribution columns
corr_df = github_df.dropna(axis=0, subset = ['Issues','Pull_Requests','Commits','Contributors'])[['Issues','Pull_Requests','Commits','Contributors']]

# set figure size and dpi
fig, ax = plt.subplots(figsize=(6,4), dpi=100)

# plot the correlation in a heatmap
sns.heatmap(corr_df.corr(), linewidths=0.1, vmax=1.0, square=True, linecolor='white', annot=True, cmap='summer');
fig.suptitle('Correlation between the contribution columns',fontsize=16, color = '#333F4B');

Padhma

# create a list of top 10 users with more repositories
users_with_more_repos = github_df.groupby('User_Name').size().nlargest(n=10).reset_index(name='Count')['User_Name'].to_list()

# create a dataframe using users_with_more_repos list
more_repos_users = github_df[github_df['User_Name'].isin(users_with_more_repos)][['Topic','User_Name','Star']]

# plot data
sns.countplot(data=more_repos_users,y='User_Name',palette = 'cool',order=more_repos_users['User_Name'].value_counts().index);

# set figure size and dpi

Padhma

# set figure size and dpi
fig, ax = plt.subplots(figsize=(8,4), dpi=100)

# set seaborn theme for background grids
sns.set_theme('paper')

# plot the data
sns.regplot(data=github_df, x='Watch', y='Fork', color='purple');

# set x and y-axis labels and title

Padhma

# set figure size and dpi
fig, ax = plt.subplots(figsize=(8,4), dpi=100)

# set seaborn theme for background grids
sns.set_theme('paper')

# plot the data
sns.regplot(data=github_df, x='Star', y='Fork', color='purple');

# set x and y-axis labels and title

Padhma

# set figure size and dpi
fig, ax = plt.subplots(figsize=(6,4), dpi=100)

# add colors to edge
plt.rcParams['axes.edgecolor']='#333F4B'

# customize spines and tick parameters
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)