PR#26: refactored some modules - fedora-contributor-trends

fedora-contributor-trends

#26 refactored some modules

Opened 2 years ago by mykaah. Modified 2 years ago

mykaah/fedora-contributor-trends main into main

addedd requirements

mykaah • 2 years ago

c6b571e

refactored some modules

mykaah • 2 years ago

8ac3167

create-all-time-userstats-csv.sh

file modified

+1 -1

		`@@ -12,6 +12,6 @@`

		`python new-and-old-users-report.py --csvh $(( $STARTWEEK - 1 )) \| tee data/contributor-count.csv`
		`for week in $(seq $STARTWEEK $ENDWEEK ); do`
		`- python new-and-old-users-report.py --csv $week \| tee -a data/contributor-count.csv`
		`+ python3 new-and-old-users-report.py --csv $week \| tee -a data/contributor-count.csv`
		`done`

generate-activity-charts.py

file modified

+94 -383

		`@@ -1,14 +1,12 @@`
		`#!/usr/bin/python3`
		`import os`
		`-`
		`import matplotlib as m`
		`- import matplotlib.pyplot as plt`
		`- import pandas`
		`+ import pandas as pd`
		`+ from utils import rename, get_pct, plot, save`

		`m.use("Agg")`

		`m.rcParams["font.size"] = 12`
		`- m.rcParams["font.family"] = "Overpass"`
		`m.rcParams["legend.frameon"] = False`

		`try:`
		`@@ -16,419 +14,132 @@`
		`except OSError:`
		`pass`

		`- datagit = pandas.read_csv(`
		`+ # =============================datagit==============================`
		`+ new_names = {`
		`+ "users1": "Top 1%",`
		`+ "users9": "Next 9%",`
		`+ "users40": "Next 40%",`
		`+ "userrest": "Remaining 50%",`
		`+ }`
		`+ color = ["#579d1c", "#ffd320", "#ff420e", "#004586"]`
		`+`
		`+ datagit = pd.read_csv(`
		`"data/org.fedoraproject.prod.git.receive.bucketed-activity.csv", parse_dates=[0]`
		`)`
		`datagit.set_index("weekstart", inplace=True)`

		`- graph = (`
		`- datagit[["users1", "users9", "users40", "userrest"]]`
		`- .rename(`
		`- columns={`
		`- "users1": "Top 1%",`
		`- "users9": "Next 9%",`
		`- "users40": "Next 40%",`
		`- "userrest": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- yticks=range(0, 301, 25),`
		`- )`
		`- )`
		`- # graph.legend(ncol=4)`
		`- # totally abusing this.`
		`- plt.suptitle("Number of Contributors Making Changes to Packages Each Week", fontsize=24)`
		`- graph.set_title("Grouped by Quarterly Activity Level of Each Contributor", fontsize=16)`
		`- graph.set_xlabel("")`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/git.user.count.svg", dpi=300)`
		`+ columns = ["users1", "users9", "users40", "userrest"]`
		`+ df = rename(datagit, columns, new_names)`

		`- #############################################`
		`+ yticks = range(0, 301, 25)`
		`+ suptitle = "Number of Contributors Making Changes to Packages Each Week"`
		`+ title = "Grouped by Quarterly Activity Level of Each Contributor"`
		`+ path = "images/git.user.count.svg"`

		`- datagit["msgstotal"] = datagit[["msgs1", "msgs9", "msgs40", "msgsrest"]].sum(1)`
		`- datagit["msgs1%"] = 100 * datagit["msgs1"] / datagit["msgstotal"]`
		`- datagit["msgs9%"] = 100 * datagit["msgs9"] / datagit["msgstotal"]`
		`- datagit["msgs40%"] = 100 * datagit["msgs40"] / datagit["msgstotal"]`
		`- datagit["msgsrest%"] = 100 * datagit["msgsrest"] / datagit["msgstotal"]`
		`+ graph = plot(df, suptitle, title, color, yticks=yticks)`
		`+ save(graph, path)`

		`+ get_pct(datagit)`

		`m.rcParams["legend.frameon"] = True`
		`- graph = (`
		`- datagit[["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]]`
		`- .rename(`
		`- columns={`
		`- "msgs1%": "Top 1%",`
		`- "msgs9%": "Next 9%",`
		`- "msgs40%": "Next 40%",`
		`- "msgsrest%": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- ylim=(0, 100),`
		`- )`
		`- )`
		`- plt.suptitle(`
		`- "Percent of Package Changes Each Week From Each Activity Level Group", fontsize=24`
		`- )`
		`- graph.set_title("", fontsize=16)`
		`- graph.set_xlabel("")`
		`-`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/git.activity.share.svg", dpi=300)`
		`-`
		`- ###############################################`
		`-`
		`- # graph=datagit[['newusercount']].rename(columns={"newusercount": "New Users"}).plot.area(figsize=(16, 9),`
		`- # color='#579d1c',`
		`- # grid=True,legend=False)`
		`- # plt.suptitle("New Packaging Contributor Count Per Week",fontsize=24)`
		`- # graph.set_title('')`
		`- # graph.set_xlabel('')`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/git.newusers.svg',dpi=300)`
		`-`
		`- #############################################`
		`-`
		`- # datagit['newuseractions%']=100*datagit['newuseractions']/datagit['msgstotal']`
		`- # datagit['monthuseractions%']=100*datagit['monthuseractions']/datagit['msgstotal']`
		`- # datagit['yearuseractions%']=100*datagit['yearuseractions']/datagit['msgstotal']`
		`- # datagit['olderuseractions%']=100*datagit['olderuseractions']/datagit['msgstotal']`
		`-`
		`-`
		`- # m.rcParams['legend.frameon'] = True`
		`- # graph=datagit[['newuseractions%','monthuseractions%','yearuseractions%','olderuseractions%']][42:]`
		`- # .rename(columns={"newuseractions%": "New This Week","monthuseractions%":"New This Month",`
		`- # "yearuseractions%":"New This Year","olderuseractions%":"Old School"})`
		`- # .plot.area(figsize=(16, 9),`
		`- # color=['#579d1c','#ffd320', '#ff420e', '#004586' ],`
		`- # grid=True,ylim=(0,100))`
		`- # plt.suptitle("Percent of Package Changes Each Week By Time Since Packager's First Action",fontsize=24)`
		`- # graph.set_title("",fontsize=16)`
		`- # graph.set_xlabel('')`
		`- #`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/git.activity.length.svg',dpi=300)`
		`- #`
		`- ################################################################################################################`
		`- ################################################################################################################`
		`-`
		`- databodhi = pandas.read_csv(`
		`+`
		`+ columns = ["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]`
		`+ df = rename(datagit, columns, new_names)`
		`+ ylim = (0, 100)`
		`+ suptitle = "Percent of Package Changes Each Week From Each Activity Level Group"`
		`+ title = ""`
		`+ path = "images/git.activity.share.svg"`
		`+ graph = plot(df, suptitle, title, color, ylim=ylim)`
		`+ save(graph, path)`
		`+`
		`+ # =============================databodhi==============================`
		`+ databodhi = pd.read_csv(`
		`"data/org.fedoraproject.prod.bodhi.update.comment.bucketed-activity.csv",`
		`parse_dates=[0],`
		`)`
		`databodhi.set_index("weekstart", inplace=True)`

		`- graph = (`
		`- databodhi[["users1", "users9", "users40", "userrest"]]`
		`- .rename(`
		`- columns={`
		`- "users1": "Top 1%",`
		`- "users9": "Next 9%",`
		`- "users40": "Next 40%",`
		`- "userrest": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- yticks=range(0, 301, 25),`
		`- )`
		`- )`
		`- # graph.legend(ncol=4)`
		`- # totally abusing this.`
		`- plt.suptitle(`
		`- "Number of Contributors Providing Feedback on Package Updates Each Week",`
		`- fontsize=24,`
		`- )`
		`- graph.set_title("Grouped by Quarterly Activity Level of Each Contributor", fontsize=16)`
		`- graph.set_xlabel("")`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/bodhi.user.count.svg", dpi=300)`
		`+ columns = ["users1", "users9", "users40", "userrest"]`
		`+ df = rename(databodhi, columns, new_names)`

		`- #############################################`
		`+ yticks = range(0, 301, 25)`
		`+ suptitle = "Number of Contributors Providing Feedback on Package Updates Each Week"`
		`+ title = "Grouped by Quarterly Activity Level of Each Contributor"`
		`+ path = "images/bodhi.user.count.svg"`
		`+ graph = plot(df, suptitle, title, color, yticks=yticks)`
		`+ save(graph, path)`

		`- databodhi["msgstotal"] = databodhi[["msgs1", "msgs9", "msgs40", "msgsrest"]].sum(1)`
		`- databodhi["msgs1%"] = 100 * databodhi["msgs1"] / databodhi["msgstotal"]`
		`- databodhi["msgs9%"] = 100 * databodhi["msgs9"] / databodhi["msgstotal"]`
		`- databodhi["msgs40%"] = 100 * databodhi["msgs40"] / databodhi["msgstotal"]`
		`- databodhi["msgsrest%"] = 100 * databodhi["msgsrest"] / databodhi["msgstotal"]`
		`+ get_pct(databodhi)`


		`m.rcParams["legend.frameon"] = True`
		`- graph = (`
		`- databodhi[["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]]`
		`- .rename(`
		`- columns={`
		`- "msgs1%": "Top 1%",`
		`- "msgs9%": "Next 9%",`
		`- "msgs40%": "Next 40%",`
		`- "msgsrest%": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- ylim=(0, 100),`
		`- )`
		`- )`
		`- plt.suptitle(`
		`- "Percent of Update Feedback Each Week From Each Activity Level Group", fontsize=24`
		`- )`
		`- graph.set_title("", fontsize=16)`
		`- graph.set_xlabel("")`
		`-`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/bodhi.activity.share.svg", dpi=300)`
		`-`
		`- ###############################################`
		`-`
		`- # graph=databodhi[['newusercount']].rename(columns={"newusercount": "New Users"}).plot.area(figsize=(16, 9),`
		`- # color='#579d1c',`
		`- # grid=True,legend=False)`
		`- # plt.suptitle("New Update Testing Contributor Count Per Week",fontsize=24)`
		`- # graph.set_title('')`
		`- # graph.set_xlabel('')`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/bodhi.newusers.svg',dpi=300)`
		`-`
		`- #############################################`
		`-`
		`- # databodhi['newuseractions%']=100*databodhi['newuseractions']/databodhi['msgstotal']`
		`- # databodhi['monthuseractions%']=100*databodhi['monthuseractions']/databodhi['msgstotal']`
		`- # databodhi['yearuseractions%']=100*databodhi['yearuseractions']/databodhi['msgstotal']`
		`- # databodhi['olderuseractions%']=100*databodhi['olderuseractions']/databodhi['msgstotal']`
		`-`
		`-`
		`- # m.rcParams['legend.frameon'] = True`
		`- # graph=databodhi[['newuseractions%','monthuseractions%','yearuseractions%','olderuseractions%']][42:]`
		`- # .rename(columns={"newuseractions%": "New This Week","monthuseractions%":"New This Month",`
		`- # "yearuseractions%":"New This Year","olderuseractions%":"Old School"}).plot.area(figsize=(16, 9),`
		`- # color=['#579d1c','#ffd320', '#ff420e', '#004586' ],`
		`- # grid=True,ylim=(0,100))`
		`- # plt.suptitle("Percent of Update Feedback Each Week By Time Since Packager's First Action",fontsize=24)`
		`- # graph.set_title("",fontsize=16)`
		`- # graph.set_xlabel('')`
		`- #`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/bodhi.activity.length.svg',dpi=300)`
		`-`
		`-`
		`- ################################################################################################################`
		`- ################################################################################################################`
		`-`
		`- datawiki = pandas.read_csv(`
		`+ columns = ["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]`
		`+ df = rename(databodhi, columns, new_names)`
		`+`
		`+ ylim = (0, 100)`
		`+ suptitle = "Percent of Update Feedback Each Week From Each Activity Level Group"`
		`+ title = ""`
		`+ path = "bodhi.activity.share.svg"`
		`+ graph = plot(df, suptitle, title, color, ylim=ylim)`
		`+ save(graph, path)`
		`+`
		`+ # =============================datawiki==============================`
		`+ datawiki = pd.read_csv(`
		`"data/org.fedoraproject.prod.wiki.article.edit.bucketed-activity.csv",`
		`parse_dates=[0],`
		`)`
		`datawiki.set_index("weekstart", inplace=True)`

		`- graph = (`
		`- datawiki[["users1", "users9", "users40", "userrest"]]`
		`- .rename(`
		`- columns={`
		`- "users1": "Top 1%",`
		`- "users9": "Next 9%",`
		`- "users40": "Next 40%",`
		`- "userrest": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- yticks=range(0, 301, 25),`
		`- )`
		`- )`
		`- # graph.legend(ncol=4)`
		`- # totally abusing this.`
		`- plt.suptitle("Number of Wiki Editors Each Week", fontsize=24)`
		`- graph.set_title("Grouped by Quarterly Activity Level of Each Contributor", fontsize=16)`
		`- graph.set_xlabel("")`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/wiki.user.count.svg", dpi=300)`
		`+ columns = ["users1", "users9", "users40", "userrest"]`
		`+ df = rename(datawiki, columns, new_names)`

		`- #############################################`
		`+ yticks = range(0, 301, 25)`
		`+ suptitle = "Number of Wiki Editors Each Week"`
		`+ title = "Grouped by Quarterly Activity Level of Each Contributor"`
		`+ path = "images/wiki.user.count.svg"`
		`+ graph = plot(df, suptitle, title, color, yticks=yticks)`
		`+ save(graph, path)`

		`- datawiki["msgstotal"] = datawiki[["msgs1", "msgs9", "msgs40", "msgsrest"]].sum(1)`
		`- datawiki["msgs1%"] = 100 * datawiki["msgs1"] / datawiki["msgstotal"]`
		`- datawiki["msgs9%"] = 100 * datawiki["msgs9"] / datawiki["msgstotal"]`
		`- datawiki["msgs40%"] = 100 * datawiki["msgs40"] / datawiki["msgstotal"]`
		`- datawiki["msgsrest%"] = 100 * datawiki["msgsrest"] / datawiki["msgstotal"]`
		`+ get_pct(datawiki)`


		`m.rcParams["legend.frameon"] = True`
		`- graph = (`
		`- datawiki[["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]]`
		`- .rename(`
		`- columns={`
		`- "msgs1%": "Top 1%",`
		`- "msgs9%": "Next 9%",`
		`- "msgs40%": "Next 40%",`
		`- "msgsrest%": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- ylim=(0, 100),`
		`- )`
		`- )`
		`- plt.suptitle(`
		`- "Percent of Wiki Edits Each Week From Each Activity Level Group", fontsize=24`
		`- )`
		`- graph.set_title("", fontsize=16)`
		`- graph.set_xlabel("")`
		`-`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/wiki.activity.share.svg", dpi=300)`
		`-`
		`- ###############################################`
		`-`
		`- # graph=datawiki[['newusercount']].rename(columns={"newusercount": "New Users"}).plot.area(figsize=(16, 9),`
		`- # color='#579d1c',`
		`- # grid=True,legend=False)`
		`- # plt.suptitle("New Wiki Contributor Count Per Week",fontsize=24)`
		`- # graph.set_title('')`
		`- # graph.set_xlabel('')`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/wiki.newusers.svg',dpi=300)`
		`- ###############################################`
		`-`
		`- # graph=datawiki[['newusercount']].rename(columns={"newusercount": "New Users"}).plot.area(figsize=(16, 9),`
		`- # color='#579d1c',`
		`- # grid=True,legend=False)`
		`- # plt.suptitle("New Wiki Contributor Count Per Week",fontsize=24)`
		`- # graph.set_title('')`
		`- # graph.set_xlabel('')`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/wiki.newusers.svg',dpi=300)`
		`-`
		`- #############################################`
		`-`
		`- # datawiki['newuseractions%']=100*datawiki['newuseractions']/datawiki['msgstotal']`
		`- # datawiki['monthuseractions%']=100*datawiki['monthuseractions']/datawiki['msgstotal']`
		`- # datawiki['yearuseractions%']=100*datawiki['yearuseractions']/datawiki['msgstotal']`
		`- # datawiki['olderuseractions%']=100*datawiki['olderuseractions']/datawiki['msgstotal']`
		`-`
		`-`
		`- # m.rcParams['legend.frameon'] = True`
		`- # graph=datawiki[['newuseractions%','monthuseractions%','yearuseractions%','olderuseractions%']][42:]`
		`- # .rename(columns={"newuseractions%": "New This Week","monthuseractions%":"New This Month",`
		`- # "yearuseractions%":"New This Year","olderuseractions%":"Old School"}).plot.area(figsize=(16, 9),`
		`- # color=['#579d1c','#ffd320', '#ff420e', '#004586' ],`
		`- # grid=True,ylim=(0,100))`
		`- # plt.suptitle("Percent of Wiki Edits Each Week By Time Since Editor's First Edit",fontsize=24)`
		`- # graph.set_title("",fontsize=16)`
		`- # graph.set_xlabel('')`
		`- #`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/wiki.activity.length.svg',dpi=300)`
		`-`
		`- ###############################################`
		`- ###############################################`
		`- datapagure = pandas.read_csv(`
		`+ columns = ["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]`
		`+ df = rename(datawiki, columns, new_names)`
		`+`
		`+ ylim = (0, 100)`
		`+ suptitle = "Percent of Wiki Edits Each Week From Each Activity Level Group"`
		`+ title = ""`
		`+ path = "wiki.user.count.svg"`
		`+ graph = plot(df, suptitle, title, color, ylim=ylim)`
		`+ save(graph, path)`
		`+`
		`+`
		`+ # =============================datapagure==============================`
		`+ datapagure = pd.read_csv(`
		`"data/io.pagure.prod.pagure.git.receive.bucketed-activity.csv", parse_dates=[0]`
		`)`
		`datapagure.set_index("weekstart", inplace=True)`
		`+ columns = ["users1", "users9", "users40", "userrest"]`
		`+ df = rename(datapagure, columns, new_names)`

		`- graph = (`
		`- datapagure[["users1", "users9", "users40", "userrest"]]`
		`- .rename(`
		`- columns={`
		`- "users1": "Top 1%",`
		`- "users9": "Next 9%",`
		`- "users40": "Next 40%",`
		`- "userrest": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- yticks=range(0, 25, 5),`
		`- )`
		`- )`
		`- # graph.legend(ncol=4)`
		`- # totally abusing this.`
		`- plt.suptitle("Number of Contributors Making Commits to Pagure Each Week", fontsize=24)`
		`- graph.set_title("Grouped by Quarterly Activity Level of Each Contributor", fontsize=16)`
		`- graph.set_xlabel("")`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/pagure.user.count.svg", dpi=300)`
		`+ yticks = range(0, 25, 5)`
		`+ suptitle = "Number of Contributors Making Commits to Pagure Each Week"`
		`+ title = "Grouped by Quarterly Activity Level of Each Contributor"`
		`+ path = "images/pagure.user.count.svg"`
		`+ graph = plot(df, suptitle, title, color, yticks=yticks)`
		`+ save(graph, path)`

		`- #############################################`
		`-`
		`- datapagure["msgstotal"] = datapagure[["msgs1", "msgs9", "msgs40", "msgsrest"]].sum(1)`
		`- datapagure["msgs1%"] = 100 * datapagure["msgs1"] / datapagure["msgstotal"]`
		`- datapagure["msgs9%"] = 100 * datapagure["msgs9"] / datapagure["msgstotal"]`
		`- datapagure["msgs40%"] = 100 * datapagure["msgs40"] / datapagure["msgstotal"]`
		`- datapagure["msgsrest%"] = 100 * datapagure["msgsrest"] / datapagure["msgstotal"]`
		`+ get_pct(datapagure)`


		`m.rcParams["legend.frameon"] = True`
		`- graph = (`
		`- datapagure[["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]]`
		`- .rename(`
		`- columns={`
		`- "msgs1%": "Top 1%",`
		`- "msgs9%": "Next 9%",`
		`- "msgs40%": "Next 40%",`
		`- "msgsrest%": "Remaining 50%",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#579d1c", "#ffd320", "#ff420e", "#004586"],`
		`- grid=True,`
		`- ylim=(0, 100),`
		`- )`
		`- )`
		`- plt.suptitle(`
		`- "Percent of Pagure Commits Each Week From Each Activity Level Group", fontsize=24`
		`- )`
		`- graph.set_title("", fontsize=16)`
		`- graph.set_xlabel("")`
		`-`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/pagure.activity.share.svg", dpi=300)`
		`-`
		`- ###############################################`
		`-`
		`- # graph=datapagure[['newusercount']].rename(columns={"newusercount": "New Users"}).plot.area(figsize=(16, 9),`
		`- # color='#579d1c',`
		`- # grid=True,legend=False)`
		`- # plt.suptitle("New Pagure Contributor Count Per Week",fontsize=24)`
		`- # graph.set_title('')`
		`- # graph.set_xlabel('')`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/pagure.newusers.svg',dpi=300)`
		`-`
		`- #############################################`
		`-`
		`- # datapagure['newuseractions%']=100*datapagure['newuseractions']/datapagure['msgstotal']`
		`- # datapagure['monthuseractions%']=100*datapagure['monthuseractions']/datapagure['msgstotal']`
		`- # datapagure['yearuseractions%']=100*datapagure['yearuseractions']/datapagure['msgstotal']`
		`- # datapagure['olderuseractions%']=100*datapagure['olderuseractions']/datapagure['msgstotal']`
		`-`
		`-`
		`- # m.rcParams['legend.frameon'] = True`
		`- # graph=datapagure[['newuseractions%','monthuseractions%','yearuseractions%','olderuseractions%']][42:]`
		`- # .rename(columns={"newuseractions%": "New This Week","monthuseractions%":"New This Month",`
		`- # "yearuseractions%":"New This Year","olderuseractions%":"Old School"}).plot.area(figsize=(16, 9),`
		`- # color=['#579d1c','#ffd320', '#ff420e', '#004586' ],`
		`- # grid=True,ylim=(0,100))`
		`- # plt.suptitle("Percent of Pagure Commits Each Week By Time Since Packager's First Action",fontsize=24)`
		`- # graph.set_title("",fontsize=16)`
		`- # graph.set_xlabel('')`
		`- #`
		`- # fig=graph.get_figure()`
		`- # fig.savefig('images/pagure.activity.length.svg',dpi=300)`
		`+ columns = ["msgs1%", "msgs9%", "msgs40%", "msgsrest%"]`
		`+ df = rename(datapagure, columns, new_names)`
		`+`
		`+ ylim = (0, 100)`
		`+ suptitle = "Percent of Pagure Commits Each Week From Each Activity Level Group"`
		`+ title = ""`
		`+ path = "images/pagure.activity.share.svg"`
		`+ graph = plot(df, suptitle, title, color, ylim=ylim)`
		`+ save(graph, path)`

generate-contributor-charts.py

file modified

+45 -64

		`@@ -2,13 +2,13 @@`
		`import os`

		`import matplotlib as m`
		`- import matplotlib.pyplot as plt`
		`- import pandas`
		`+ import pandas as pd`
		`+`
		`+ from utils import rename, save, plot`

		`m.use("Agg")`

		`m.rcParams["font.size"] = 12`
		`- m.rcParams["font.family"] = "Overpass"`
		`m.rcParams["legend.frameon"] = True`

		`try:`
		`@@ -16,75 +16,56 @@`
		`except OSError:`
		`pass`

		`- data = pandas.read_csv("data/contributor-count.csv", parse_dates=[0])`
		`- data.set_index("weekstart", inplace=True)`
		`-`
		`+ new_names = {`
		`+ "oldactive": "Old School",`
		`+ "midactive": "Intermediate",`
		`+ "newactive": "New Contributors",`
		`+ }`
		`+ color = ["#579d1c", "#ffd320", "#ff420e", "#004586"]`

		`- graph = (`
		`- data[["oldactive", "midactive", "newactive"]]`
		`- .rename(`
		`- columns={`
		`- "oldactive": "Old School",`
		`- "midactive": "Intermediate",`
		`- "newactive": "New Contributors",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#ff420e", "#ffd320", "#579d1c"], # '#004586'`
		`- grid=True,`
		`- stacked=True,`
		`- yticks=range(0, 451, 25),`
		`- )`
		`- )`
		`- data[["rawcount"]].rename(`
		`- columns={"rawcount": "All Contributors\nincluding less active"}`
		`- ).plot(figsize=(16, 9), ax=graph, yticks=range(0, 426, 25))`
		`+ data = pd.read_csv("data/contributor-count.csv", parse_dates=[0])`
		`+ data.set_index("weekstart", inplace=True)`

		`- graph.xaxis.grid(True, which="minor", linestyle="-", linewidth=0.25)`
		`- graph.yaxis.grid(True, which="major", linestyle="-", linewidth=0.25)`
		`+ columns = ["oldactive", "midactive", "newactive"]`
		`+ df = rename(data, columns)`

		`- plt.suptitle("Fedora Contributors by Week", fontsize=24)`
		`- graph.set_title(`
		`- "Stacked graph of contributors with measured activity each week — and at least 13 weeks total in the last year.\n"`
		`+ yticks = range(0, 451, 25)`
		`+ suptitle = "Fedora Contributors by Week"`
		`+ title = (`
		`+ "Stacked graph of contributors with measured activity each week — and at least 13 weeks total in the \`
		`+ last year.\n"`
		`"“Old school” contributors have been active for longer than two years; new contributors, less than one.\n"`
		`- "Blue line shows all contributors active this week regardless of amount of other activity.",`
		`- fontsize=12,`
		`+ "Blue line shows all contributors active this week regardless of amount of other activity."`
		`)`
		`- graph.set_xlabel("")`
		`-`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/active-contributors-by-week.svg", dpi=300)`
		`+ path = "images/active-contributors-by-week.svg"`

		`-`
		`- graph = (`
		`- data[["oldcore", "midcore", "newcore"]]`
		`- .rename(`
		`- columns={`
		`- "oldcore": "Old School",`
		`- "midcore": "Intermediate",`
		`- "newcore": "New Contributors",`
		`- }`
		`- )`
		`- .plot.area(`
		`- figsize=(16, 9),`
		`- color=["#ff420e", "#ffd320", "#579d1c"], # '#004586'`
		`- grid=True,`
		`- stacked=True,`
		`- yticks=range(0, 101, 25),`
		`- )`
		`+ color = ["#ff420e", "#ffd320", "#579d1c"]`
		`+ new_names = {"rawcount": "All Contributors\nincluding less active"}`
		`+ graph = plot(df, suptitle, title, yticks=yticks, color=color, stacked=True)`
		`+ rename(df, columns=["rowcount"], new_names=new_names).plot(`
		`+ figsize=(16, 9), ax=graph, yticks=range(0, 426, 25)`
		`)`
		`+ save(graph, path)`

		`- graph.xaxis.grid(True, which="minor", linestyle="-", linewidth=0.25)`
		`- graph.yaxis.grid(True, which="major", linestyle="-", linewidth=0.25)`
		`+ columns = ["oldcore", "midcore", "newcore"]`
		`+ new_names = new_names = {`
		`+ "oldcore": "Old School",`
		`+ "midcore": "Intermediate",`
		`+ "newcore": "New Contributors",`
		`+ }`
		`+ df = rename(data, columns, new_names=new_names)`

		`- plt.suptitle("Core Fedora Contributors by Week", fontsize=24)`
		`- graph.set_title(`
		`- "Stacked graph of contributors with measured activity this week — and at least 13 weeks total in the last year.\n"`
		`+ yticks = range(0, 101, 25)`
		`+ suptitle = "Core Fedora Contributors by Week"`
		`+ title = (`
		`+ "Stacked graph of contributors with measured activity this week — and at least 13 weeks total in the \`
		`+ last year.\n"`
		`"Old school contributors have been active for longer than two years; new contributors, less than one.\n"`
		`- "“Core” means part of the set doing about ⅔s of all actions over the past year.",`
		`- fontsize=12,`
		`+ "“Core” means part of the set doing about ⅔s of all actions over the past year."`
		`)`
		`- graph.set_xlabel("")`
		`- fig = graph.get_figure()`
		`- fig.savefig("images/active-core-contributors-by-week.svg", dpi=300)`
		`+ path = "images/active-core-contributors-by-week.svg"`
		`+`
		`+ color = ["#ff420e", "#ffd320", "#579d1c"]`
		`+ new_names = {"rawcount": "All Contributors\nincluding less active"}`
		`+ graph = plot(df, suptitle, title, yticks=yticks, color=color, stacked=True)`
		`+ save(graph, path)`

get-weekly-user-stats.sh

file modified

+9 -9

		`@@ -1,11 +1,11 @@`
		`#!/bin/sh`

		`- until python weekly-user-activity.py org.fedoraproject.prod.irc.karma; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.git.receive; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.bodhi.update.comment; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.wiki.article.edit; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.infragit.receive; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.fedoratagger.rating.update; do sleep 5; done`
		`- until python weekly-user-activity.py io.pagure.prod.pagure.git.receive; do sleep 5; done`
		`- until python weekly-user-activity.py io.pagure.prod.pagure.issue.new; do sleep 5; done`
		`- until python weekly-user-activity.py org.fedoraproject.prod.fedbadges.badge.award; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.irc.karma; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.git.receive; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.bodhi.update.comment; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.wiki.article.edit; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.infragit.receive; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.fedoratagger.rating.update; do sleep 5; done`
		`+ until python3 weekly-user-activity.py io.pagure.prod.pagure.git.receive; do sleep 5; done`
		`+ until python3 weekly-user-activity.py io.pagure.prod.pagure.issue.new; do sleep 5; done`
		`+ until python3 weekly-user-activity.py org.fedoraproject.prod.fedbadges.badge.award; do sleep 5; done`

utils.py

file modified

+38

		`@@ -1,4 +1,7 @@`
		`import requests`
		`+ import pandas as pd`
		`+ import matplotlib.pyplot as plt`
		`+ from typing import Dict, List`

		`url = "https://apps.fedoraproject.org/datagrepper/raw"`

		`@@ -38,3 +41,38 @@`
		`raise ValueError("Ran out of retries")`
		`for message in data.get("raw_messages", []):`
		`yield message`
		`+`
		`+`
		`+ def rename(df: pd.DataFrame, columns: List, new_names: Dict) -> pd.DataFrame:`
		`+ df.rename(columns=new_names)`
		`+ return df[columns]`
		`+`
		`+`
		`+ def get_pct(df: pd.DataFrame, columns: List = ["msgs1", "msgs9", "msgs40", "msgsrest"]):`
		`+ df["msgstotal"] = df[columns].sum(1)`
		`+ total = df["msgstotal"]`
		`+ data_list = columns`
		`+ for i in data_list:`
		`+ df[i + "%"] = 100 * df[i] / total`
		`+`
		`+`
		`+ def plot(df, suptitle: str, title: str, color, **kwargs) -> None:`
		`+ graph = df.plot.area(`
		`+ figsize=(16, 9),`
		`+ color=color,`
		`+ grid=False,`
		`+ yticks=kwargs.get("yticks", None),`
		`+ stacked=kwargs.get("stacked", True),`
		`+ ylim=kwargs.get("ylim", None),`
		`+ )`
		`+ plt.suptitle(suptitle, fontsize=24)`
		`+ graph.set_title(title, fontsize=16)`
		`+ graph.set_xlabel("")`
		`+ graph.xaxis.grid(True, which="minor", linestyle="-", linewidth=0.25)`
		`+ graph.yaxis.grid(True, which="major", linestyle="-", linewidth=0.25)`
		`+ return graph`
		`+`
		`+`
		`+ def save(graph, path: str) -> None:`
		`+ fig = graph.get_figure()`
		`+ fig.savefig(path, dpi=300)`

weekly-user-activity.py

file modified

+4 -4

		`@@ -112,7 +112,7 @@`
		`bucketcsv.flush()`

		`while starttime < datetime.datetime.now() + datetime.timedelta(`
		`- 42`
		`+ 42`
		`): # weeks in the future because see below`
		`endtime = starttime + datetime.timedelta(7)`
		`weekinfo = WeekActions(`
		`@@ -129,7 +129,7 @@`
		`)`

		`msgcachefile = (`
		`- "cache/" + discriminant + "." + starttime.strftime("%Y-%m-%d") + ".pickle"`
		`+ "cache/" + discriminant + "." + starttime.strftime("%Y-%m-%d") + ".pickle"`
		`)`

		`if os.path.exists(msgcachefile):`
		`@@ -300,7 +300,7 @@`
		`)`

		`if any(`
		`- (bucketscores[1], bucketscores[2], bucketscores[3], bucketscores[4])`
		`+ (bucketscores[1], bucketscores[2], bucketscores[3], bucketscores[4])`
		`):`
		`bucketcsv.write(`
		`"%s,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d\n"`
		`@@ -330,7 +330,7 @@`
		`# unless we're in the future, save the weekly userdata csv`
		`if starttime < datetime.datetime.now():`
		`with open(`
		`- "data/weekly/%s.userdata.%05d.csv" % (discriminant, weeknum), "w"`
		`+ "data/weekly/%s.userdata.%05d.csv" % (discriminant, weeknum), "w"`
		`) as weekcsv:`
		`weekcsv.write(`
		`"%s,%s,%s,%s\n" % ("user", "actions", "firstseen", "lastseen")`

mykaah commented 2 years ago

Hello! In this pr , I have
- refactored certain modules used to generate charts.
- changed all python calls in the scripts to python3 to avoid dependency errors.
- Removed some commented code to tidy up the project.

I hope to get a review from you on tasks done so far. Thanks
cc @mattdm

mykaah commented 2 years ago

Oh! Must be an error. I'll check it out and rectify it. Thank you very much.

On Sun, May 2, 2021, 7:29 PM Josseline Perdomo pagure@pagure.io wrote:

josseline commented on the pull-request: refactored some modules that
you are following:
Nice! @mykaah but, why did you delete the requirements file?

To reply, visit the link below or just reply to this email
https://pagure.io/fedora-contributor-trends/pull-request/26