#futurewarnings
Explore tagged Tumblr posts
Visit Tumblr Blog
Explore Tumblr blogs with no restrictions, modern design and the best experience.
Last Seen Tumblr Blogs
Fun Fact
Average visit duration of Tumblr.com is 10 mins and 25 secs.
Text
L’Ultima Guerra: La Fine dell’Umanità è Vicina
Stanno facendo di tutto per promuovere il "Kit di sopravvivenza" per la Grande Guerra che verrà: l’ultima guerra, quella che spazzerà via l’intera umanità.
Fascisti, oligarchi, capitalisti senza scrupoli, burocrati guerrafondai e imperialisti assassini cercano in ogni modo di giustificare l'inizio della fine. Un'epoca in cui bombe atomiche cadranno dal cielo, la radioattività contaminerà il suolo e i mari, e l’umanità sarà condannata a vivere senza cibo, senza acqua, senza cure, in un mondo devastato da malattie e sofferenza.
Sono loro, i signori della guerra e della corruzione, che ci stanno trascinando verso l’abisso: verso l’era delle atomiche, la guerra definitiva che potrebbe annientare il 99% della popolazione mondiale in meno di un mese.
#youtube#FineDelMondo#UltimaGuerra#ApocalisseNucleare#PoliticaCorrotta#NoAllaGuerra#CrisiGlobale#ResistenzaUmana#AntiImperialismo#PeaceNotWar#StopNuclearWar#FutureWarning#SurvivalKit#GuerraMondiale#Dystopia#NuclearApocalypse
0 notes
Text
警告やエラーを解決していく その1
## 警告やエラーを解決していく WARNING: you should not skip torch test unless you want CPU to work. F:\StabilityMatrix\Data\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\timm\models\layers\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers",…
0 notes
Text
Mediante un mensaje FutureWarning tambien se puede indicar cambios en los valores predeterminados de los parametros de funciones. https://www.analyticslane.com/2024/01/22/que-son-y-como-manejar-los-errores-futurewarning-en-python/
0 notes
Text
'Dates Misinterpreted' (Yeshuah)
‘Dates Misinterpreted’ (Yeshuah)
Dates Misinterpreted (Yeshuah) they are weakening their stance a surrender in malice against an unbeknowing people too busy living an unproductive life a covering up of suspicion don't you see why don't you see a waywardness buried tyre did this babylon did this egypt did this so many in ignorance buried under their decorated arrogance so it is a stone thrown to the masses if I† came…
View On WordPress
#futurewarnings#God#Good#Jesus#love#Psalms 1#Psalms 14#Psalms 144#teaching#virus#war#warning#Yeshuah
0 notes
Text
#ai#artificialgeneralintelligence#artificial intelligence#future#the future#artificial art#technology#tech news#news#business news#latest news#breaking news#google#godfatherofgoogle#warning#globalwarning#futurewarning#future warning#global warning#be careful#take a warning
9 notes
·
View notes
Text
🚨 Elon Musk's Shocking Warning: AI Dependency Could Doom Humanity! Are We Heading Toward a Real-Life Idiocracy? 🤖📉😱
🚀 Elon Musk recently dropped a 💣 with a tweet that shook the 🌐! In it, he warned about the ⚠️ of overreliance on AI & automation 🤖, hinting at a future straight out of the dystopian 🎞️ "Idiocracy" 🥤📺🤦♂️. He also mentioned E.M. Forster's 1909 story "The Machine Stops" 🛑, painting a dark picture of society's downfall 🌆🔥.
Elon Musk’s recent tweet 🐦 highlights a potential concern that is mirrored in the 2006 movie “Idiocracy” 📽️. The film presents a dystopian future where the general population becomes increasingly unintelligent over time 🧠⏳, ultimately leading to the collapse of society. Musk’s tweet suggests that a similar scenario could arise if we become too reliant on AI and automation 🤖, eventually forgetting how these machines work 🔧.
One way that AI could contribute to the decline of society, as portrayed in “Idiocracy”, is by fostering a culture of complacency and overreliance on technology 📱💻. As AI systems become more advanced, people may rely on them for decision-making, problem-solving, and general knowledge 🧩. Over time, this could lead to a gradual erosion of critical thinking skills 💭 and a diminishing ability to solve problems independently. As individuals lose their ability to think critically and innovate, the overall intellectual capacity of society could decrease 📉.
Moreover, as AI and automation take over more tasks 📈, there may be a decline in the need for human labor 💼, leading to fewer opportunities for individuals to engage in meaningful work 🛠️. This could result in a loss of a sense of purpose and a growing disconnection from the world around them 🌍. Without the necessity to learn, adapt, and overcome challenges, people may become intellectually stagnant and less capable of addressing complex issues that require human ingenuity 🧠.
Musk also referenced “The Machine Stops” 🛑, a 1909 science fiction short story by E. M. Forster that depicts a world where humanity has become entirely dependent on a global machine for all aspects of their lives 🌐🤖. In this story, people live in isolated cells and interact only through technology 📲, while the machine takes care of their every need. This dependence on technology ultimately leads to the decline of human culture, intellect, and innovation 📚.
“The Machine Stops” illustrates how an overreliance on technology can lead to the erosion of society. The story serves as a cautionary tale ⚠️, warning against the dangers of placing too much trust in machines and losing touch with our humanity ❤️. Similarly, Musk’s tweets suggest that relying too heavily on AI and automation could create a world where humans gradually lose their capacity for independent thought, creativity, and innovation 🎨🎭.
Elon Musk’s recent tweets bring attention to the potential dangers of becoming too dependent on AI and automation 🚨. Drawing parallels to “Idiocracy” and “The Machine Stops” 🎞️📖, Musk warns that allowing technology to take over all aspects of our lives could lead to the decline of society. To prevent this outcome, it is crucial to strike a balance between harnessing the benefits of AI and automation while maintaining a strong focus on human innovation, critical thinking, and the preservation of our intellectual abilities 🧠💡.
1 note
·
View note
Text
Hard Candy (~Misfits AU~)
Chapter 27: Epilogue - Back to The Future
Warning: Language, alcohol.
a/n: This has been a wild ride! I just wanna thank you all for your support and for being so incredible, Lydia is such a dear character to me and it’s great to see people falling in love with her story. Oh, and even though this is the last chapter of Hard Candy, the story isn’t over, keep an eye out for tons of drabbles and one shots, and a brand new series (hopefully) coming soon.
(Hard Candy Masterlist)
- I'm really lovin' this new color on you, Lyddie - Nathan played with my pink hair.
- Yeah, it was time for a little change, wasn't it? Today marks the start of a new part of my life... The part I know absolutely nothing about. After all, today's the day.
- The day? What d'you mean?
- The day we first kissed, when I confessed to you. Actually, it was right here, at this very table, at this very pub. After Simon left with Lisha, you promised to get me home safely by the end of the night, we talked for hours and hours until it finally happened.
- No shit! Wow, it seemed so far away when you told me about it, can't believe the day arrived, life is just passin' me by... I'm gettin' old, aren't I?
- You look fine to me - I winked and blew him a kiss.
- So, why are we here today? I thought you'd wanna forget it... Forget how much of a wanker I was for lettin' you go.
- Well, I normally would, but I think I owe someone an explanation.
- Who?
I looked pointedly at the door as my younger self walked towards our table. Nathan's face lit up upon seeing young Lydia, it was kinda cute to see him reacting like this instead of her for once.
- I think you get the picture?
- Oh, yeah... I get the whole picture - he smirked.
- Hey Lolli, hey Nathan - Lydia smiled as she joined us in the booth.
- Hi, Lyds - I took her hand - how are you?
- I'm good, just practicing a lot, I'm actually playing one of your songs for my university audition next week, Shape of You.
- Were you goin' to university? - Nathan frowned, slightly guilty.
- Yeah - I whispered - but it was okay.
- I have a good feeling about it, maybe it will be better than secondary school... - She joked.
- Are you excited to become an aunt? - I asked.
- Very! Simon promised me he would let me be the godmother - she clapped with excitement.
- That's really nice... - I was trying to gather the nerve to say what I had to say, the whole reason why I asked her to come in the first place - So, there's something important we need to talk to you about.
- Oh, is everything ok? - Lydia seemed worried.
- Sure, brilliant - Nathan chuckled, still a little hypnotized by her.
- So... I know you're into Nathan - I shrugged.
- What? - She blushed furiously, sputtering a bunch of nonsense - I'm not... He's just... I think he's... But not...
- Lydia, it's ok - I stroked her hair gently - it's natural and I'm not mad, really. Believe me, I understand exactly the way you feel.
- That's adorable - Nathan bit his lip teasingly - I love how jittery you get when you're around me... Lollipop.
Her breath hitched when she heard that name being directed at her. She stared at him agape and I saw her pupils dilate at least ten times their normal size.
If I'm being honest his sultry tone did something to me as well, that man knew exactly how to get us both riled up and ready. How could I blame her?
- That's... That's weird, is this a wind-up? - She looked scared.
- Here - Nathan got closer to her, placing his hand on the back of her neck - does this look like a wind-up?
He leaned in and kissed her, she stood still for a few seconds before melting into his arms. It was funny to watch, her fingers quickly making their way to Nathan's curls, her body pushing to be closer to his. It was almost like I could feel that rush, her stomach filling up with butterflies just like mine did so long ago.
- Oh my God, oh Jesus, okay - she panted as he let her go and wrapped his arm around me - what is happening? Why is your husband kissing me? Why are you ok with him cheating on you? I heard that famous people are weird, but...
- Well, Lydia - I grinned widely - he's not cheating on me, because we're the same person.
- We're what?
- My name is not Lolli or Lyddie, it's actually Blossom Lydia Bellamy Young, I was born in Wertham, on November 22nd, 1996, and funny enough, I have a birthmark that resembles a microphone.
I turned to show her my left shoulder and she tilted her head with the most confused expression I've ever seen on my face.
- Oh my God, people did always say I look a lot like you... So what does that mean? - She gulped nervously - How did you do this? How did we do this?
- Well, I fell in love with this twat, just like you, but when that happened he wasn't married to me. He was married to another woman, he had a family with her. He turned me down after saying he loved me, he said that in another life we could've been happy together, so I decided to make this other life real.
- What did you do?
- I sold everything I owned and bought myself a power, one-way time travel. I went back to 2009, got myself arrested and sentenced to community service, and that's when I met my Nathan.
- That's amazing - she looked between us - but why are you telling me this?
- I thought it would be only fair for you to have the same chance I did, to go back and be with the man we love. That is if you don't mind giving me the place of our nephew's godmother...
- So you're saying I should go back in time?
- Do you want to?
- Is it dangerous?
- Extremely, but I'm here, I'm alive, and I've never been better.
- What if he doesn't fall in love with me?
- That's impossible - Nathan shook his head - there's no way this could ever happen. I knew I was fallin' from the moment she called me "lanky kid".
He rubbed his thumb against the back of my hand with a sweet smile. I never knew that, can't believe he still remembers that day.
- Well... I do, I wanna go.
- Alright, I'll arrange everything. I'll write down some instructions for you on how to keep the timeline in place, and you can go two weeks from now. There's a guy I know who can transfer the power from me to you, you just have to promise me one thing.
- Anything - she nodded enthusiastically.
- When this day comes for you, today, you need to tell young Lydia the same thing I told you and offer her the same chance I'm giving you.
- Sure, I can do that.
- Just don't give up when I mess things up, alright? - Nathan tucked a strand of her hair behind her ear - I know I will, several times, but I do love you, before and after.
- I promise I won't - she gazed at him lovingly - can I possibly get... Another kiss?
- Such a little tart... - Nathan pulled her close and I laughed - You can never get enough, can ya?
- Shut up, you cocky bastard! - I rolled my eyes.
Nate kissed Lydia passionately, smearing once again her lipstick all over their mouths. Her chest was heaving and I could see that sparkle, the true happiness in her eyes, that thing that finally made me feel truly beautiful.
- And one more for the road - Nathan kissed her one last time.
- I can't believe this is happening - she looked down, catching her breath.
- You better believe it, Lollipop - he purred - actually, I think you deserve a little somethin' special. Maybe I should get a drink, a little snack, and then we both...
- SHE'S NOT READY! - I covered his mouth with my hand - She'll die of embarrassment if you say what you were about to say.
- Alright, touchy - he mocked - don't worry, young me will know exactly what to do to get rid o'that shyness.
- What are you guys talking about? - She widened her eyes.
- Nothin', you'll know soon enough - Nathan waggled his brows with a cheeky grin.
- Don't be scared of the lightning, yeah? - I whispered - It'll hurt like a bastard, but it's just the beginning of the biggest adventure of your life.
Tag list: @crisis-of-joy @elliethesuperfruitlover @misskittysmagicportal
#misfits#Misfits tv#misfits imagine#misfits fanfic#misfits nathan#nathan young#nathan young x oc#nathan x lydia#hard candy#imagine#fanfic
27 notes
·
View notes
Note
Ooo! Fun!! Who is your crush Kiibo? I'll just take a guess and say it's Miu, but just to be sure, I want to hear the answer from you. Who is your senpai Kiibo? -Chaotic Anon
[Tw Yandere Themes. No blood yet, so FutureWarning] Miu is my senpai,,,,,I love Miu very much, and would do ANYTHING to keep her mine.
1 note
·
View note
Text
pandas.DataFrameに対してstyle.set_precision()を実施すると警告が出てくるのを修正する
警告は下記の通り。
FutureWarning: this method is deprecated in favour of `Styler.format(precision=..)`
修正例
df.style.set_precision(2).highlight_min(axis=1,subset=model_names_list_JP) -> df.style.format(precision=2).highlight_min(axis=1,subset=model_names_list_JP)
理由： set_precision(<数値>) は廃止され、 .format(precision=<数値>) が採用されたため。
0 notes
Photo
Creating Graph for My Data
Summary
From the graph its clear that the distribution only contained teenagers who agreed that they have been pregnant and also showed if they were ready to get pregnant or not, turns out a larger percentage agreed to the fact that they were ready when they got pregnant.
My code
sub2["H1FP7"] = sub2["H1FP7"].astype('category')
seaborn.countplot(x="H1FP7", data=sub2) plt.xlabel(' Respondent who Have been pregnant') plt.title('Respondents who are teenagers that confirmed that they are pregnant')
#Univariate histogram for quantitative variable: seaborn.distplot(sub2["H1FP15_1"].dropna(), kde=False); plt.xlabel('Ready for pregnancy/not ready?') plt.title('Estimated number of respondent who agreed to be ready for pregnacy or not ready') ############################################################################### # Code for Week 4 Python Lesson 3 - Measures of Center & Spread
# standard deviation and other descriptive statistics for quantitative variables print ('Pregnant') desc1 = sub2['H1FP7'].describe() print (desc1)
c1= sub2.groupby('H1FP15_1').size() print (c1)
print ('Pregnant') desc2 = sub2['H1FP7'].describe() print (desc2)
c1= sub2.groupby('H1FP7').size() print (c1)
print ('mode') mode1 = sub2['H1FP7'].mode() print (mode1)
print ('mean') mean1 = sub2['H1FP15_1'].mean() print (mean1)
print ('std') std1 = sub2['H1FP15_1'].std() print (std1)
print ('min') min1 = sub2['H1FP15_1'].min() print (min1)
print ('max') max1 = sub2['H1FP15_1'].max() print (max1)
print ('median') median1 = sub2['H1FP15_1'].median() print (median1)
print ('mode') mode1 = sub2['H1FP15_1'].mode() print (mode1)
c1= sub2.groupby('H1FP7').size() print (c1)
p1 = sub2.groupby('H1FP7').size() * 100 / len(data) print (p1)
c2 = sub2.groupby('H1FP15_1').size() print (c2)
p2 = sub2.groupby('H1FP15_1').size() * 100 / len(data) print (p2)
My Code Output
ct1= data.groupby('H1FP7').size() print(ct1)
pt1 = data.groupby('H1FP7').size() * 100 / len(data) print(pt1) H1FP7 0 643 1 131 6 4 7 4058 8 1 dtype: int64 H1FP7 0 13.293364 1 2.708290 6 0.082696 7 83.894976 8 0.020674 dtype: float64
sub1=data[(data['age']>=18) & (data['age']<=25) & (data['H1FP7']==1)]
sub2 = sub1.copy()
import seaborn import matplotlib.pyplot as plt
seaborn.countplot(x="H1FP7", data=sub2) plt.xlabel(' Respondent who Have been pregnant') plt.title('Respondents who are teenagers that confirmed that they are pregnant') Out[9]: Text(0.5, 1.0, 'Respondents who are teenagers that confirmed that they are pregnant')
Figures now render in the Plots pane by default. To make them also appear inline in the Console, uncheck "Mute Inline Plotting" under the Plots pane options menu.
seaborn.distplot(sub2["H1FP15_1"].dropna(), kde=False); plt.xlabel('Ready for pregnancy/not ready?') plt.title('Estimated number of respondent who agreed to be ready for pregnacy or not ready') C:\Users\Admin\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning) Out[10]: Text(0.5, 1.0, 'Estimated number of respondent who agreed to be ready for pregnacy or not ready')
print ('Pregnant') desc1 = sub2['H1FP7'].describe() print (desc1) Pregnant count 87.0 mean 1.0 std 0.0 min 1.0 25% 1.0 50% 1.0 75% 1.0 max 1.0 Name: H1FP7, dtype: float64
print ('Pregnant') desc1 = sub2['H1FP7'].describe() print (desc1)
c1= sub2.groupby('H1FP15_1').size() print (c1)
print ('Pregnant') desc2 = sub2['H1FP7'].describe() print (desc2)
c1= sub2.groupby('H1FP7').size() print (c1)
print ('mode') mode1 = sub2['H1FP7'].mode() print (mode1)
print ('mean') mean1 = sub2['H1FP15_1'].mean() print (mean1)
print ('std') std1 = sub2['H1FP15_1'].std() print (std1)
print ('min') min1 = sub2['H1FP15_1'].min() print (min1)
print ('max') max1 = sub2['H1FP15_1'].max() print (max1)
print ('median') median1 = sub2['H1FP15_1'].median() print (median1)
print ('mode') mode1 = sub2['H1FP15_1'].mode() print (mode1)
c1= sub2.groupby('H1FP7').size() print (c1)
p1 = sub2.groupby('H1FP7').size() * 100 / len(data) print (p1)
c2 = sub2.groupby('H1FP15_1').size() print (c2)
p2 = sub2.groupby('H1FP15_1').size() * 100 / len(data) print (p2) Pregnant count 87.0 mean 1.0 std 0.0 min 1.0 25% 1.0 50% 1.0 75% 1.0 max 1.0 Name: H1FP7, dtype: float64 H1FP15_1 1 5 3 2 4 2 5 1 7 77 dtype: int64 Pregnant count 87.0 mean 1.0 std 0.0 min 1.0 25% 1.0 50% 1.0 75% 1.0 max 1.0 Name: H1FP7, dtype: float64 H1FP7 1 87 dtype: int64 mode 0 1 dtype: int64 mean 6.471264367816092 std 1.5614474535594247 min 1 max 7 median 7.0 mode 0 7 dtype: int64 H1FP7 1 87 dtype: int64 H1FP7 1 1.798636 dtype: float64 H1FP15_1 1 5 3 2 4 2 5 1 7 77 dtype: int64 H1FP15_1 1 0.103370 3 0.041348 4 0.041348 5 0.020674 7 1.591896 dtype: float64
0 notes
Text
Week 4 Creating graphs for your data
STEP 1: Create graphs of your variables one at a time (univariate graphs).
Examine both their center and spread.
STEP 2: Create a graph showing the association between your explanatory and response variables (bivariate graph).
import pandas as pd import seaborn as sns import matplotlib.pyplot as plt data = pd.read_csv('/content/gapminder.csv', low_memory=False) bindata = data.copy() data['internetuserate'] = pd.to_numeric(data['internetuserate'], errors='coerce') bindata['internetuserate'] = pd.cut(data.internetuserate, 10) data['incomeperperson'] = pd.to_numeric(data['incomeperperson'], errors='coerce') bindata['incomeperperson'] = pd.cut(data.incomeperperson, 10) data['employrate'] = pd.to_numeric(data['employrate'], errors='coerce') bindata['employrate'] = pd.cut(data.employrate, 10) data['femaleemployrate'] = pd.to_numeric(data['femaleemployrate'], errors='coerce') bindata['femaleemployrate'] = pd.cut(data.femaleemployrate, 10) data['polityscore'] = pd.to_numeric(data['polityscore'], errors='coerce') bindata['polityscore'] = data['polityscore'] sub2 = bindata.copy()
sns.distplot(data["internetuserate"].dropna(), kde=False); plt.xlabel('Internet Use Rate') plt.title('Percentage of Population with Access to the Internet') sns.plt.show()
/usr/local/lib/python3.6/dist-packages/seaborn/distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-5-a4342a87f149> in <module>() 3 plt.xlabel('Internet Use Rate') 4 plt.title('Percentage of Population with Access to the Internet') ----> 5 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() sns.distplot(data["incomeperperson"].dropna(), kde=False); plt.xlabel('Income Per Person') plt.title('GDP Per Person') sns.plt.show()
/usr/local/lib/python3.6/dist-packages/seaborn/distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-6-54db57e9a334> in <module>() 3 plt.xlabel('Income Per Person') 4 plt.title('GDP Per Person') ----> 5 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() sns.distplot(data["employrate"].dropna(), kde=False); plt.xlabel('Employment Rate') plt.title('Percentage of total population, age above 15, that has been employed during the given year.') sns.plt.show()
/usr/local/lib/python3.6/dist-packages/seaborn/distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-7-9e73a7a31906> in <module>() 3 plt.xlabel('Employment Rate') 4 plt.title('Percentage of total population, age above 15, that has been employed during the given year.') ----> 5 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
sns.distplot(data["femaleemployrate"].dropna(), kde=False); plt.xlabel('Female Employment Rate') plt.title('Percentage of Female Population with Access to the Internet') sns.plt.show()
/usr/local/lib/python3.6/dist-packages/seaborn/distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-8-84212c88bbe3> in <module>() 3 plt.xlabel('Female Employment Rate') 4 plt.title('Percentage of Female Population with Access to the Internet') ----> 5 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() sns.countplot(x="polityscore", data=data) plt.xlabel('Polity Score') plt.title("The summary measure of a country's democratic and free nature") sns.plt.show()
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-9-92fdf6792227> in <module>() 3 plt.xlabel('Polity Score') 4 plt.title("The summary measure of a country's democratic and free nature") ----> 5 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() scat1 = sns.regplot(x="internetuserate", y="incomeperperson", fit_reg=False, data=data) plt.xlabel('Internet Use Rate') plt.ylabel('Income Per Person') plt.title('Scatterplot for the Association Between Internet Use Rate and Income Per Person') sns.plt.show()
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-10-8661bffadf8a> in <module>() 4 plt.ylabel('Income Per Person') 5 plt.title('Scatterplot for the Association Between Internet Use Rate and Income Per Person') ----> 6 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() scat2 = sns.regplot(x="internetuserate", y="employrate", fit_reg=False, data=data) plt.xlabel('Internet Use Rate') plt.ylabel('Employment Rate') plt.title('Scatterplot for the Association Between Internet Use Rate and Employment Rate') sns.plt.show()
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-11-ec533021bfd1> in <module>() 4 plt.ylabel('Employment Rate') 5 plt.title('Scatterplot for the Association Between Internet Use Rate and Employment Rate') ----> 6 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
plt.figure() scat3 = sns.regplot(x="internetuserate", y="femaleemployrate", fit_reg=False, data=data) plt.xlabel('Female Employment Rate') plt.ylabel('Income Per Person') plt.title('Scatterplot for the Association Between Internet Use Rate and Female Employment Rate') sns.plt.show()
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-12-f90bc6bd752f> in <module>() 4 plt.ylabel('Income Per Person') 5 plt.title('Scatterplot for the Association Between Internet Use Rate and Female Employment Rate') ----> 6 sns.plt.show() AttributeError: module 'seaborn' has no attribute 'plt'
0 notes
Text
Assignment-02_02 (Course-02, Module-02)
Running Chi-Square Independence Test
Dataset : GapMinder
Variables
urbanrate (urbgrps after collapsing into categories)
lifeexpectancy ( lifgrps after collapsing into categories)
urbgrps : urbanrate is collapsed into categories of width 20%, hence having 5 categories (1 for 0%-20%, 2 for 20% to 40%, .... and 5 for 80% to 100%)
lifgrps : It is a two-valued variable, with value 1 if the country has life-expectancy greater than or equal ti 65% and 0 otherwise.
Research Question : Hypothesis
H0 : proportion of countries in each category of urbgrps having life-expectancy of 65+ years is equal
HA : The proportion is unequal for atleast two groups
Summary
The p-value for the Chi-square test is 0.000008, which is significantly less than 0.05. Hence we can reject the null hypothesis.
The following table shows the p-values of chi-square tests for each pair of categories.
There are 10 comparisons, hence our threshold p-value must be 0.05/10 = 0.005
It is clear that category-4 (countries with urban-rate between 60% and 80%) has significantly different life-expectancy
Output
Rows 213 columns 16 ===================================== Descriptive Statistical Analysis =====================================
===================================== Inferencial Statistical Analysis ===================================== urbgrps 1 2 3 4 5 lifgrps 0 9 24 17 6 16 1 4 22 29 52 34 G:/Data Science/Data Analysis and Interpretation (Coursera)/Codes/02-02-Assignment.py:46: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects() For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric. data['urbanrate'] = data['urbanrate'].convert_objects(convert_numeric=True) G:/Data Science/Data Analysis and Interpretation (Coursera)/Codes/02-02-Assignment.py:47: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects() For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric. data['alcconsumption'] = data['alcconsumption'].convert_objects(convert_numeric=True) G:/Data Science/Data Analysis and Interpretation (Coursera)/Codes/02-02-Assignment.py:48: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects() For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric. data['lifeexpectancy'] = data['lifeexpectancy'].convert_objects(convert_numeric=True) G:/Data Science/Data Analysis and Interpretation (Coursera)/Codes/02-02-Assignment.py:75: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects() For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric. return 0 urbgrps 1 2 3 4 5 lifgrps 0 0.692308 0.521739 0.369565 0.103448 0.320000 1 0.307692 0.478261 0.630435 0.896552 0.680000 chi-square value, p value, expected counts (28.770249676716467, 8.704036143643654e-06, 4L, array([[ 4.3943662 , 15.54929577, 15.54929577, 19.6056338 , 16.90140845], [ 8.6056338 , 30.45070423, 30.45070423, 38.3943662 , 33.09859155]])) ============================= Post-hoc test New threshold for p-value : 0.005 1 vs 2 comp1v2 1.000000 2.000000 lifgrps 0 9 24 1 4 22 comp1v2 1.000000 2.000000 lifgrps 0 0.692308 0.521739 1 0.307692 0.478261 chi-square value, p value, expected counts (0.6044210109845561, 0.43689616446201507, 1L, array([[ 7.27118644, 25.72881356], [ 5.72881356, 20.27118644]])) 1 vs 3 comp 1.000000 3.000000 lifgrps 0 9 17 1 4 29 comp 1.000000 3.000000 lifgrps 0 0.692308 0.369565 1 0.307692 0.630435 chi-square value, p value, expected counts (3.073965958790373, 0.07955517016836518, 1L, array([[ 5.72881356, 20.27118644], [ 7.27118644, 25.72881356]])) 1 vs 4 comp 1.000000 4.000000 lifgrps 0 9 6 1 4 52 comp 1.000000 4.000000 lifgrps 0 0.692308 0.103448 1 0.307692 0.896552 chi-square value, p value, expected counts (18.70646985916383, 1.524642950087753e-05, 1L, array([[ 2.74647887, 12.25352113], [10.25352113, 45.74647887]])) 1 vs 5 comp 1.000000 5.000000 lifgrps 0 9 16 1 4 34 comp 1.000000 5.000000 lifgrps 0 0.692308 0.320000 1 0.307692 0.680000 chi-square value, p value, expected counts (4.520721862348178, 0.03348669970950359, 1L, array([[ 5.15873016, 19.84126984], [ 7.84126984, 30.15873016]])) 2 vs 3 comp 2.000000 3.000000 lifgrps 0 24 17 1 22 29 comp 2.000000 3.000000 lifgrps 0 0.521739 0.369565 1 0.478261 0.630435 chi-square value, p value, expected counts (1.5839311334289814, 0.20819535296566563, 1L, array([[20.5, 20.5], [25.5, 25.5]])) 2 vs 4 comp 2.000000 4.000000 lifgrps 0 24 6 1 22 52 comp 2.000000 4.000000 lifgrps 0 0.521739 0.103448 1 0.478261 0.896552 chi-square value, p value, expected counts (19.878233856044954, 8.253469598112272e-06, 1L, array([[13.26923077, 16.73076923], [32.73076923, 41.26923077]])) 2 vs 5 comp 2.000000 5.000000 lifgrps 0 24 16 1 22 34 comp 2.000000 5.000000 lifgrps 0 0.521739 0.320000 1 0.478261 0.680000 chi-square value, p value, expected counts (3.2246459627329176, 0.07253748022033618, 1L, array([[19.16666667, 20.83333333], [26.83333333, 29.16666667]])) 3 vs 4 comp 3.000000 4.000000 lifgrps 0 17 6 1 29 52 comp 3.000000 4.000000 lifgrps 0 0.369565 0.103448 1 0.630435 0.896552 chi-square value, p value, expected counts (9.059129050611572, 0.0026138645525417546, 1L, array([[10.17307692, 12.82692308], [35.82692308, 45.17307692]])) 3 vs 5 comp 3.000000 5.000000 lifgrps 0 17 16 1 29 34 comp 3.000000 5.000000 lifgrps 0 0.369565 0.320000 1 0.630435 0.680000 chi-square value, p value, expected counts (0.08745341614906833, 0.7674399219661803, 1L, array([[15.8125, 17.1875], [30.1875, 32.8125]])) 4 vs 5 comp 4.000000 5.000000 lifgrps 0 6 16 1 52 34 comp 4.000000 5.000000 lifgrps 0 0.103448 0.320000 1 0.896552 0.680000 chi-square value, p value, expected counts (6.485275205948824, 0.01087716976280061, 1L, array([[11.81481481, 10.18518519], [46.18518519, 39.81481481]]))
Finslly The Code
import pandas import numpy import seaborn import matplotlib.pyplot as plt import statsmodels.formula.api as smf import statsmodels.stats.multicomp as multi import scipy.stats
#importing data data = pandas.read_csv('Dataset_gapminder.csv', low_memory=False)
#Set PANDAS to show all columns in DataFrame pandas.set_option('display.max_columns', None) #Set PANDAS to show all rows in DataFrame pandas.set_option('display.max_rows', None)
# bug fix for display formats to avoid run time errors pandas.set_option('display.float_format', lambda x:'%f'%x)
#printing number of rows and columns print ('Rows') print (len(data)) print ('columns') print (len(data.columns))
#------- Variables under consideration------# # alcconsumption # urbanrate # lifeexpectancy
# Setting values to numeric data['urbanrate'] = data['urbanrate'].convert_objects(convert_numeric=True) data['alcconsumption'] = data['alcconsumption'].convert_objects(convert_numeric=True) data['lifeexpectancy'] = data['lifeexpectancy'].convert_objects(convert_numeric=True)
# Categorizing urbanrate as urbgrps
def urbgrps (row): if row['urbanrate'] <= 20 : return 1 elif row['urbanrate'] <= 40 : return 2 elif row['urbanrate'] <= 60 : return 3 elif row['urbanrate'] <= 80 : return 4 else : return 5 data2['urbgrps'] = data2.apply (lambda row: urbgrps (row),axis=1) data2["urbgrps"] = data2["urbgrps"].astype('category')
# Categorizing lifeexpectancy as lifgrps
def lifgrps (row): if row['lifeexpectancy'] >= 65 : return 1 else : return 0 data2['lifgrps'] = data2.apply (lambda row: lifgrps (row),axis=1) # Setting urbgrps to numeric data2['lifgrps'] = data2['lifgrps'].convert_objects(convert_numeric=True)
# Descriptive Analysis
print ('=====================================') print ('Descriptive Statistical Analysis') print ('=====================================') seaborn.factorplot(x='urbgrps', y='lifgrps', data=data2, kind="bar", ci=None) plt.xlabel('Urban rate') plt.ylabel('Proportion of countries in group with lifeexpectancy less than 65 years')
#Inferencial Statistic
print ('=====================================') print ('Inferencial Statistical Analysis') print ('=====================================')
# contingency table of observed counts ct1=pandas.crosstab(data2['lifgrps'], data2['urbgrps']) print (ct1)
# column percentages colsum=ct1.sum(axis=0) colpct=ct1/colsum print(colpct)
# chi-square value, p value, expected counts print ('chi-square value, p value, expected counts') cs1= scipy.stats.chi2_contingency(ct1) print (cs1)
# Post-hoc Test
print ('=============================') print ('Post-hoc test') print ('New threshold for p-value : ') print (0.05/10) print ('1 vs 2') recode1_2 = {1:1, 2:2} data2['comp1v2'] = data2['urbgrps'].map(recode1_2)
ct1_2 = pandas.crosstab(data2['lifgrps'], data2['comp1v2']) print (ct1_2)
colsum1_2 = ct1_2.sum(axis=0) colpct1_2 = ct1_2/colsum1_2 print (colpct1_2)
print ('chi-square value, p value, expected counts') cs1_2 = scipy.stats.chi2_contingency(ct1_2) print (cs1_2)
# 1 vs 3 print ('1 vs 3') recode = {1:1, 3:3} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 1 vs 4 print ('1 vs 4') recode = {1:1, 4:4} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 1 vs 5 print ('1 vs 5') recode = {1:1, 5:5} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 2 vs 3 print ('2 vs 3') recode = {2:2, 3:3} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 2 vs 4 print ('2 vs 4') recode = {2:2, 4:4} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 2 vs 5 print ('2 vs 5') recode = {2:2, 5:5} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 3 vs 4 print ('3 vs 4') recode = {3:3, 4:4} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 3 vs 5 print ('3 vs 5') recode = {3:3, 5:5} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
# 4 vs 5 print ('4 vs 5') recode = {4:4, 5:5} data2['comp'] = data2['urbgrps'].map(recode)
ct = pandas.crosstab(data2['lifgrps'], data2['comp']) print (ct)
colsum = ct.sum(axis=0) colpct = ct/colsum print (colpct)
print ('chi-square value, p value, expected counts') cs = scipy.stats.chi2_contingency(ct) print (cs)
0 notes
Photo
DockerでUnity ML-Agentsを動作させてみた(v0.11.0対応) https://ift.tt/2rjOwz3
Unity ML-Agents(v0.9.1)をDocker上で動作させてみました。
UnityやUnity ML-Agentsの環境構築などは下記をご参考ください。
Macでhomebrewを使ってUnityをインストールする(Unity Hub、日本語化対応) https://cloudpack.media/42142
MacでUnity ML-Agentsの環境を構築する(v0.11.0対応) – Qiita https://cloudpack.media/50837
手順
v0.10.1まではDockerでの学習方法についてドキュメントがあったのですが、v0.11.0の時点でドキュメントが削除されています。情報としては若干古くなりますが、v0.11.0でもこちらを参考にして動作させることができます。
ml-agents/Using-Docker.md at 0.10.1 · Unity-Technologies/ml-agents https://github.com/Unity-Technologies/ml-agents/blob/0.10.1/docs/Using-Docker.md
Dockerのインストール
Dockerがインストールされていない場合、インストールします。
Macでbrewコマンド利用
> brew cask install docker (略) > docker --version Docker version 19.03.4, build 9013bf5
※Dockerを初回起動すると初期設定のためにパスワード入力が求められます。
UnityにLinuxビルドサポートコンポーネントを追加する
Unity Hubを利用してUnityにLinuxビルドサポートコンポーネントを追加します。 Unityのバージョンは2019.2.10f1を利用しています。
Unity Hubがインストールされていない場合は下記をご参考ください。
Macでhomebrewを使ってUnityをインストールする(Unity Hub、日本語化対応) https://cloudpack.media/42142
Unity Hub��プリを起動する
[インストール] > [Unityの利用するアプリ]右側にある[︙]をクリックして[モジュールを加える]を選択する
[モジュールを加える]ダイアログの[Platforms]にある[Linux Build Support]にチェックを入れて[実行]ボタンをクリックする
学習用のUnityアプリをダウンロードしてビルドする
ML-Agentsリポジトリに含まれているサンプルを学習できるようにします。
ML-Agentsリポジトリをダウンロード
適当なディレクトリにリポジトリをダウンロードする。
> mkdir 適当なディレクトリ > cd 適当なディレクトリ > git clone https://github.com/Unity-Technologies/ml-agents.git
Unityアプリからサンプルプロジェクトを開く
Unity Hubでアプリを立ち上げます。 ML-Agentsを利用するにはUnityのバージョン2017.4以上が必要となります。今回は2019.2.10f1を利用しました。
アプリが立ち上がったら「開く」ボタンから任意のディレクトリ/ml-agents/UnitySDKフォルダを選択します。
Unityエディタのバージョンによっては、アップグレードするかの確認ダイアログが立ち上がります。
「確認」ボタンをクリックして進めます。アップグレード処理に少し時間がかかります。
起動しました。
今回は、サンプルにある[3DBall]Scenesを利用します。
Unityアプリの下パネルにある[Project]タブから以下のフォルダまで開く
[Assets] > [ML-Agents] > [Examples] > [3DBall] > [Scenes]
開いたら、[3DBall]ファイルがあるので、ダブルクリックして開く
Scenes(シーン)の設定
ML-Agentsで学習させるための設定です。
Unityアプリの[Edit]メニューから[Project Settings]を開く
[Inspector]パネルで以下の設定を確認する
[Resolution and Presentation]の[Run In Background]がチェックされている
[Display Resolution Dialog]がDisableになっている
ビルド設定
Unityアプリの[File]メニューから[Build Settings]を選択して[Build Settings]ダイアログを開く
[Add Open Scenes]をクリックする
[Scenes In Build]で[ML-Agents/Examples/3DBall/Scenes/3DBall]にチェックを入れる
[Platform]でPC, Mac & Linux Standalone が選択されていることを確認する
[Target Platform]をLinuxに変更する
[Architecture]をx86_64に変更する
[Server Build]にチェックを入れる
[Build]ボタンをクリックする
ファイル保存ダイアログで以下を指定してビルドを開始する
ファイル名: 3DBall
フォルダ名: 任意のディレクトリ/ml-agents/unity-volume
すると、unity-volumeに以下フォルダ・ファイルが出力されます。
ls 任意のディレクトリ/ml-agents/unity-volume 3DBall.x86_64 3DBall_Data
ハイパーパラメーターファイルの用意
ハイパーパラメーターファイルをunity-volumeフォルダにコピーしておきます。
> cp ml-agents/config/trainer_config.yaml ml-agents/unity-volume/
Dockerイメージを作成する
すでにDockerfileが用意されているので、docker buildするだけ。楽々ですね。 ml-agents-on-dockerはイメージ名となりますので、任意でOKです。
> docker build -t ml-agents-on-docker ./ml-agents (略) Removing intermediate container c1384ee9d5a6 ---> 9ff8832e88dc Step 19/20 : EXPOSE 5005 ---> Running in 53253a272fb4 Removing intermediate container 53253a272fb4 ---> f0b43146ad36 Step 20/20 : ENTRYPOINT ["mlagents-learn"] ---> Running in f80f7504b790 Removing intermediate container f80f7504b790 ---> 9caddd5a62b1 Successfully built 9caddd5a62b1 Successfully tagged ml-agents-on-docker:latest > docker images REPOSITORY TAG IMAGE ID CREATED SIZE ml-agents-on-docker latest 9caddd5a62b1 2 minutes ago 1.23GB
注意点
ml-agentsディレクトリ直下でdocker buildコマンドを実行するとエラーになるのでご注意ください。
> cd ml-agents > docker build -t ml-agents-on-docker . error checking context: 'file ('/Users/xxx/xxxxx/ml-agents/UnitySDK/Temp') not found or excluded by .dockerignore'.
v0.10.0からPython 3.7.xにも対応しましたが、Dockerfileを覗いてみるとPyhtonのバージョンは3.6.4のままでした。
Dockerfile一部抜粋
ENV PYTHON_VERSION 3.6.4
Dockerコンテナの実行
ビルドできたら実行してみます。
bashの場合
# ml-agents-3dball: コンテナ名(任意) # ml-agents-on-docker: Dockerでビルド時に付けたイメージ名 # 3DBall: Unityでビルド時に付けたアプリの名前(拡張子なし) > cd ml-agents > docker run -it --rm \ --name ml-agents-3dball \ --mount type=bind,source="$(pwd)"/unity-volume,target=/unity-volume \ -p 5005:5005 \ -p 6006:6006 \ ml-agents-on-docker:latest \ --docker-target-name=unity-volume \ --env=3DBall \ --train \ trainer_config.yaml
mlagents-learnコマンドの--docker-target-nameオプションはdocker runコマンドの--workdir(-w)に置き換えることもできます。
> docker run -it --rm \ --name ml-agents-3dball \ --mount type=bind,source="$(pwd)"/unity-volume,target=/unity-volume \ -w /unity-volume \ -p 5005:5005 \ -p 6006:6006 \ ml-agents-on-docker:latest \ --env=3DBall \ --train \ trainer_config.yaml
fishシェルで実行する場合は、"$(pwd)"を"$PWD"に置き換えます。
fishの場合
> cd ml-agents > docker run -it --rm \ --name ml-agents-3dball \ --mount type=bind,source="$PWD"/unity-volume,target=/unity-volume \ -p 5005:5005 \ -p 6006:6006 \ ml-agents-on-docker:latest \ --docker-target-name=unity-volume \ --env=3DBall \ --train \ trainer_config.yaml
実行すると、学習が始まります。 trainer_config.yamlのmax_stepsで指定されているステップ数が完了するか、ctrl + cキーで学習が終了します。
> docker run (略) ▄▄▄▓▓▓▓ ╓▓▓▓▓▓▓█▓▓▓▓▓ ,▄▄▄m▀▀▀' ,▓▓▓▀▓▓▄ ▓▓▓ ▓▓▌ ▄▓▓▓▀' ▄▓▓▀ ▓▓▓ ▄▄ ▄▄ ,▄▄ ▄▄▄▄ ,▄▄ ▄▓▓▌▄ ▄▄▄ ,▄▄ ▄▓▓▓▀ ▄▓▓▀ ▐▓▓▌ ▓▓▌ ▐▓▓ ▐▓▓▓▀▀▀▓▓▌ ▓▓▓ ▀▓▓▌▀ ^▓▓▌ ╒▓▓▌ ▄▓▓▓▓▓▄▄▄▄▄▄▄▄▓▓▓ ▓▀ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▄ ▓▓▌ ▀▓▓▓▓▀▀▀▀▀▀▀▀▀▀▓▓▄ ▓▓ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▐▓▓ ^█▓▓▓ ▀▓▓▄ ▐▓▓▌ ▓▓▓▓▄▓▓▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▓▄ ▓▓▓▓` '▀▓▓▓▄ ^▓▓▓ ▓▓▓ └▀▀▀▀ ▀▀ ^▀▀ `▀▀ `▀▀ '▀▀ ▐▓▓▌ ▀▀▀▀▓▄▄▄ ▓▓▓▓▓▓, ▓▓▓▓▀ `▀█▓▓▓▓▓▓▓▓▓▌ ¬`▀▀▀█▓ INFO:mlagents.trainers:CommandLineOptions(debug=False, num_runs=1, seed=-1, env_path='3DBall', run_id='ppo', load_model=False, train_model=True, save_freq=50000, keep_checkpoints=5, base_port=5005, num_envs=1, curriculum_folder=None, lesson=0, slow=False, no_graphics=False, multi_gpu=False, trainer_config_path='trainer_config.yaml', sampler_file_path=None, docker_target_name='unity-volume', env_args=None, cpu=False) INFO:mlagents.envs: 'Ball3DAcademy' started successfully! Unity Academy name: Ball3DAcademy Number of Training Brains : 0 Reset Parameters : gravity -> 9.8100004196167 scale -> 1.0 mass -> 1.0 (略) 2019-11-07 05:31:38.593118: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-11-07 05:31:38.604956: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2400000000 Hz 2019-11-07 05:31:38.607307: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x39ccf70 executing computations on platform Host. Devices: 2019-11-07 05:31:38.607465: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): <undefined>, <undefined> (略) 2019-11-07 05:31:40.131532: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. INFO:mlagents.envs:Hyperparameters for the PPOTrainer of brain 3DBall: trainer: ppo batch_size: 64 beta: 0.001 buffer_size: 12000 epsilon: 0.2 hidden_units: 128 lambd: 0.99 learning_rate: 0.0003 learning_rate_schedule: linear max_steps: 5.0e4 memory_size: 256 normalize: True num_epoch: 3 num_layers: 2 time_horizon: 1000 sequence_length: 64 summary_freq: 1000 use_recurrent: False vis_encode_type: simple reward_signals: extrinsic: strength: 1.0 gamma: 0.99 summary_path: /unity-volume/summaries/ppo_3DBall model_path: /unity-volume/models/ppo-0/3DBall keep_checkpoints: 5 WARNING:tensorflow:From /ml-agents/mlagents/trainers/trainer.py:223: The name tf.summary.text is deprecated. Please use tf.compat.v1.summary.text instead. WARNING:tensorflow:From /ml-agents/mlagents/trainers/trainer.py:223: The name tf.summary.text is deprecated. Please use tf.compat.v1.summary.text instead. INFO:mlagents.trainers: ppo: 3DBall: Step: 1000. Time Elapsed: 10.062 s Mean Reward: 1.167. Std of Reward: 0.724. Training. (略) INFO:mlagents.trainers: ppo: 3DBall: Step: 10000. Time Elapsed: 109.367 s Mean Reward: 36.292. Std of Reward: 28.127. Training. (略) INFO:mlagents.trainers: ppo: 3DBall: Step: 49000. Time Elapsed: 520.514 s Mean Reward: 100.000. Std of Reward: 0.000. Training. (略) Converting /unity-volume/models/ppo-0/3DBall/frozen_graph_def.pb to /unity-volume/models/ppo-0/3DBall.nn IGNORED: Cast unknown layer IGNORED: StopGradient unknown layer GLOBALS: 'is_continuous_control', 'version_number', 'memory_size', 'action_output_shape' IN: 'vector_observation': [-1, 1, 1, 8] => 'sub_3' IN: 'epsilon': [-1, 1, 1, 2] => 'mul_1' OUT: 'action', 'action_probs' DONE: wrote /unity-volume/models/ppo-0/3DBall.nn file. INFO:mlagents.trainers:Exported /unity-volume/models/ppo-0/3DBall.nn file INFO:mlagents.envs:Environment shut down with return code 0.
WARNING がかなり出力されますが、学習できました。
TensorBoard を利用して学習の進捗を視覚的に確認することもできます。
> docker exec -it \ ml-agents-3dball \ tensorboard \ --logdir=/unity-volume/summaries \ --host=0.0.0.0 (略) _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /usr/local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) TensorBoard 1.14.0 at http://0.0.0.0:6006/ (Press CTRL+C to quit)
学習結果をアプリに組み込む
学習結果は、ml-agents/unity-volumeフォルダ内に保存されます。 それをUnityアプリに組み込むことで学習結果をUnityアプリに反映できます。
> ls unity-volume/ 3DBall.x86_64 3DBall_Data csharp_timers.json models summaries trainer_config.yaml > tree unity-volume/models/ unity-volume/models/ └── ppo-0 ├── 3DBall │ ├── checkpoint │ ├── frozen_graph_def.pb │ ├── model-50000.cptk.data-00000-of-00001 │ ├── model-50000.cptk.index │ ├── model-50000.cptk.meta │ ├── model-50001.cptk.data-00000-of-00001 │ ├── model-50001.cptk.index │ ├── model-50001.cptk.meta │ └── raw_graph_def.pb └── 3DBall.nn 2 directories, 10 files
Unityアプリの設定
Playerの設定を行います。
Unityアプリの[Edit]メニューから[Project Settings]を選択する
[Inspector]ビューの[Other Settings]欄で以下を確認・設定する
Scripting BackendがMonoになっている
Api Conpatibility Levelが.NET 4.xになっている
学習結果ファイルの取り込み
ターミナルかFinderで学習結果を以下フォルダにコピーします。
学習結果ファイル: models/ppo-0/3DBall.nn
保存先: UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/
※すでに保存先に3DBall.nnファイルが存在していますので、リネームします。
> cp models/ppo-0/3DBall.nn ml-agents/UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall_new.nn
Unityアプリの下パネルにある[Project]タブから以下のフォルダまで開く
[Assets] > [ML-Agents] > [Examples] > [3DBall] > [Scenes]
開いたら、[3DBall]ファイルがあるので、ダブルクリックして開く
[Hierarchy]パネルから[Agent]を選択する
Unityアプリの[Project]パネルで以下フォルダを選択する
[Assets] > [ML-Agents] > [Examples] > [3DBall] > [TFModels]
Unityアプリの[Inspector]パネルにある[Model]という項目に[TFModels]フォルダ内の3DBall_new.nnファイルをドラッグ＆ドロップする
Unity上部にある[
]ボタンをクリックする
これで、学習結果が組み込まれた状態でアプリが起動します。
参考
Macでhomebrewを使ってUnityをインストールする(Unity Hub、日本語化対応) https://cloudpack.media/42142
MacでUnity ML-Agentsの環境を構築する(v0.11.0対応) – Qiita https://cloudpack.media/50837
ml-agents/Using-Docker.md at 0.10.1 · Unity-Technologies/ml-agents https://github.com/Unity-Technologies/ml-agents/blob/0.10.1/docs/Using-Docker.md
元記事はこちら
「DockerでUnity ML-Agentsを動作させてみた(v0.11.0対応)」
December 23, 2019 at 12:00PM
0 notes
Text
Australia vs Pakistan: ‘Yasir Shah & Shan Masood were probably yawning’ - Wasim Akram lashes out at Pak fielders - cricket
Legendary cricketer Wasim Akram lashed out as Pakistan players for their sloppy fielding display during the second Test against Australia at Adelaide Oval. Pakistan fielders were guilty of giving away runs as Australia piled on the misery, scoring 589/3d in their first essay of Day-Night Test. David Warner was the chief architect for Australia as he slammed a majestic triple century the power hosts to his humongous score. Akram wasn’t happy with Pakistan’s effort in the field and let his feelings known while commentating during the Test. Also Read: Warner breaks Bradman’s record with unique triple hundred against Pakistan“Shaheen Shah was in la la land at fine leg,” Akram said. “Yasir Shah and Shan Masood were probably yawning. That’s the problem with Pakistan cricket. They should be on the ball.”“Nobody was backing up and you as a fielder, it doesn’t matter how inexperienced you are, you set yourself, new batsman in, they just came out, I’ll probably start five-ten yards inside the boundary line not on the boundary,” he added. Whoops! #AUSvPAK | https://t.co/0QSefkJERk pic.twitter.com/HpEwgwlm1H— cricket.com.au (@cricketcomau) November 29, 2019 Warner broke records for fun as a hapless Pakistan bowling unit was sent on a leather hunt on Day 2 of the day/night Test. At one point Warner looked set to break the highest ever Test score of 400 by Brian Lara but Australia captain Tim Paine decided otherwise. Warner remained unbeaten on 335 off 418 balls when Australia declared at 589 for 3.Also Read: ‘There is absolute clarity,’ Sourav Ganguly comments on MS Dhoni’s futureWarner went past Don Bradman and Mark Taylor’s 334-run mark, becoming the second highest scorer for Australia after Matthew Hayden’s 380 against Zimbabwe in 2003.Warner also broke Don Bradman’s 88-year-old record for the highest score at the Adelaide Oval. Bradman had scored 299 in 1931-32, which remained the highest individual score at Adelaide Oval till Warner took matters in his own hands. Source link Read the full article
0 notes
Text
Testing a Potential Moderator
1.1 ANOVA CODE
#post hoc ANOVA
import pandas
import numpy
import statsmodels.formula.api as smf
import statsmodels.stats.multicomp as multi
data = pandas.read_csv(‘addhealth_pds.csv’, low_memory=False)
print(“converting variables to numeric”)
data[“H1SU1”] = data[“H1SU1”].convert_objects(convert_numeric=True)
data[“H1NB5”] = data[“H1NB5”].convert_objects(convert_numeric=True)
data[“H1NB6”] = data[“H1NB6”].convert_objects(convert_numeric=True)
print(“Coding missing values”)
data[“H1SU1”] = data[“H1SU1”].replace(6, numpy.nan)
data[“H1SU1”] = data[“H1SU1”].replace(9, numpy.nan)
data[“H1SU1”] = data[“H1SU1”].replace(8, numpy.nan)
data[“H1NB5”] = data[“H1NB5”].replace(6, numpy.nan)
data[“H1NB6”] = data[“H1NB6”].replace(6, numpy.nan)
data[“H1NB6”] = data[“H1NB6”].replace(8, numpy.nan)
#F-Statistic
model1 = smf.ols(formula='H1SU1 ~ C(H1NB6)’, data=data)
results1 = model1.fit()
print (results1.summary())
sub1 = data[['H1SU1’, 'H1NB6’]].dropna()
print ('means for H1SU1 by happiness level in neighbourhood’)
m1= sub1.groupby('H1NB6’).mean()
print (m1)
print ('standard deviation for H1SU1 by happiness level in neighbourhood’)
sd1 = sub1.groupby('H1NB6’).std()
print (sd1)
#more tahn 2 lvls
sub2 = sub1[['H1SU1’, 'H1NB6’]].dropna()
model2 = smf.ols(formula='H1SU1 ~ C(H1NB6)’, data=sub2).fit()
print (model2.summary())
print ('2: means for H1SU1 by happiness level in neighbourhood’)
m2= sub2.groupby('H1NB6’).mean()
print (m2)
print ('2: standard deviation for H1SU1 by happiness level in neighbourhood’)
sd2 = sub2.groupby('H1NB6’).std()
print (sd2)
mc1 = multi.MultiComparison(sub2['H1SU1’], sub2 ['H1NB6’])
res1 = mc1.tukeyhsd()
print(res1.summary())
1.2 ANOVA RESULTS
converting variables to numeric
Coding missing values
OLS Regression Results
==============================================================================
Dep. Variable: H1SU1 R-squared: 0.019
Model: OLS Adj. R-squared: 0.018
Method: Least Squares F-statistic: 31.16
Date: Sat, 24 Aug 2019 Prob (F-statistic): 9.79e-26
Time: 17:16:11 Log-Likelihood: -2002.8
No. Observations: 6426 AIC: 4016.
Df Residuals: 6421 BIC: 4049.
Df Model: 4
Covariance Type: nonrobust
===================================================================================
coef std err t P>|t| [0.025 0.975]
———————————————————————————–
Intercept 0.2850 0.024 11.976 0.000 0.238 0.332
C(H1NB6)[T.2.0] -0.0800 0.029 -2.713 0.007 -0.138 -0.022
C(H1NB6)[T.3.0] -0.1192 0.025 -4.688 0.000 -0.169 -0.069
C(H1NB6)[T.4.0] -0.1615 0.025 -6.519 0.000 -0.210 -0.113
C(H1NB6)[T.5.0] -0.2033 0.025 -8.191 0.000 -0.252 -0.155
==============================================================================
Omnibus: 2528.245 Durbin-Watson: 1.952
Prob(Omnibus): 0.000 Jarque-Bera (JB): 7313.190
Skew: 2.173 Prob(JB): 0.00
Kurtosis: 5.903 Cond. No. 15.0
==============================================================================
Warnings:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
means for H1SU1 by happiness level in neighbourhood
H1SU1
H1NB6
1.0 0.284974
2.0 0.204986
3.0 0.165814
4.0 0.123478
5.0 0.081707
standard deviation for H1SU1 by happiness level in neighbourhood
H1SU1
H1NB6
1.0 0.452576
2.0 0.404252
3.0 0.372050
4.0 0.329057
5.0 0.273980
/For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
data[“H1SU1”] = data[“H1SU1”].convert_objects(convert_numeric=True)
For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
data[“H1NB5”] = data[“H1NB5”].convert_objects(convert_numeric=True)
For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
data[“H1NB6”] = data[“H1NB6”].convert_objects(convert_numeric=True)
OLS Regression Results
==============================================================================
Dep. Variable: H1SU1 R-squared: 0.019
Model: OLS Adj. R-squared: 0.018
Method: Least Squares F-statistic: 31.16
Date: Sat, 24 Aug 2019 Prob (F-statistic): 9.79e-26
Time: 17:16:11 Log-Likelihood: -2002.8
No. Observations: 6426 AIC: 4016.
Df Residuals: 6421 BIC: 4049.
Df Model: 4
Covariance Type: nonrobust
===================================================================================
coef std err t P>|t| [0.025 0.975]
———————————————————————————–
Intercept 0.2850 0.024 11.976 0.000 0.238 0.332
C(H1NB6)[T.2.0] -0.0800 0.029 -2.713 0.007 -0.138 -0.022
C(H1NB6)[T.3.0] -0.1192 0.025 -4.688 0.000 -0.169 -0.069
C(H1NB6)[T.4.0] -0.1615 0.025 -6.519 0.000 -0.210 -0.113
C(H1NB6)[T.5.0] -0.2033 0.025 -8.191 0.000 -0.252 -0.155
==============================================================================
Omnibus: 2528.245 Durbin-Watson: 1.952
Prob(Omnibus): 0.000 Jarque-Bera (JB): 7313.190
Skew: 2.173 Prob(JB): 0.00
Kurtosis: 5.903 Cond. No. 15.0
==============================================================================
Warnings:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
2: means for H1SU1 by happiness level in neighbourhood
H1SU1
H1NB6
1.0 0.284974
2.0 0.204986
3.0 0.165814
4.0 0.123478
5.0 0.081707
2: standard deviation for H1SU1 by considered suicide in past 12 months
H1SU1
H1NB6
1.0 0.452576
2.0 0.404252
3.0 0.372050
4.0 0.329057
5.0 0.273980
Multiple Comparison of Means - Tukey HSD,FWER=0.05
=============================================
group1 group2 meandiff lower upper reject
———————————————
1.0 2.0 -0.08 -0.1604 0.0004 False
1.0 3.0 -0.1192 -0.1885 -0.0498 True
1.0 4.0 -0.1615 -0.2291 -0.0939 True
1.0 5.0 -0.2033 -0.271 -0.1356 True
2.0 3.0 -0.0392 -0.0925 0.0142 False
2.0 4.0 -0.0815 -0.1326 -0.0304 True
2.0 5.0 -0.1233 -0.1745 -0.0721 True
3.0 4.0 -0.0423 -0.0731 -0.0115 True
3.0 5.0 -0.0841 -0.1152 -0.0531 True
4.0 5.0 -0.0418 -0.0687 -0.0149 True
———————————————
1.3 ANOVA summary
Model Interpretation for ANOVA:
To determine the association between my quantitative response variable (if the respondent considered suicide in the past 12 months) and categorical explanatory variable (happiness level in the respondent’s neighbourhood) I performed an ANOVA test found that those who were most unhappy in their neighbourhood were most likely to have considered suicide (Mean= 0.284974, s.d ±0.452576), F=31.16, p< 9.79e-26).
Code for anova and moderator
import numpy
import pandas
import statsmodels.formula.api as smf
import statsmodels.stats.multicomp as multi
import seaborn
import matplotlib.pyplot as plt
data = pandas.read_csv('addhealth_pds.csv', low_memory=False)
print("converting variables to numeric")
data["H1NB5"] = data["H1SU4"].astype('category')
data["H1NB6"] = data["H1SU2"].convert_objects(convert_numeric=True)
print("Coding missing values")
data["H1SU2"] = data["H1SU2"].replace(7, numpy.nan)
data["H1SU2"] = data["H1SU2"].replace(8, numpy.nan)
data["H1SU4"] = data["H1SU4"].replace(6, numpy.nan)
data["H1SU4"] = data["H1SU4"].replace(7, numpy.nan)
data["H1SU4"] = data["H1SU4"].replace(8, numpy.nan)
data["H1SU5"] = data["H1SU5"].replace(6, numpy.nan)
data["H1SU5"] = data["H1SU5"].replace(7, numpy.nan)
data["H1SU5"] = data["H1SU5"].replace(8, numpy.nan)
sub2=data[(data['H1SU5']=='0')]
sub3=data[(data['H1SU5']=='1')]
print ('association between friends suicide attemps and number of suicide attemps if friend was UNSUCCESSFUL in attempt')
model2 = smf.ols(formula='H1SU4 ~ C(H1SU2)', data=sub2).fit()
print (model2.summary())
print ('association between friends suicide attemps and number of suicide attemps if friend was SUCECSSFUL in attempt')
model3 = smf.ols(formula='H1SU4 ~ C(H1SU2)', data=sub3).fit()
print (model3.summary())
ANOVA with moderator results:
runfile('/Users/tyler2k/Downloads/Data Analysis Course/Course 2 Annova and Post Hoc.py', wdir='/Users/tyler2k/Downloads/Data Analysis Course')
converting variables to numeric
Coding missing values
association between friends suicide attemps and number of suicide attemps if friend was UNSUCCESSFUL in attempt
/Users/tyler2k/Downloads/Data Analysis Course/Course 2 Annova and Post Hoc.py:25: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects()
For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
Traceback (most recent call last):
File "<ipython-input-30-7bac10fffda5>", line 1, in <module>
runfile('/Users/tyler2k/Downloads/Data Analysis Course/Course 2 Annova and Post Hoc.py', wdir='/Users/tyler2k/Downloads/Data Analysis Course')
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 786, in runfile
execfile(filename, namespace)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 110, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "/Users/tyler2k/Downloads/Data Analysis Course/Course 2 Annova and Post Hoc.py", line 47, in <module>
model2 = smf.ols(formula='H1SU4 ~ C(H1SU2)', data=sub2).fit()
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/statsmodels/base/model.py", line 155, in from_formula
missing=missing)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/statsmodels/formula/formulatools.py", line 65, in handle_formula_data
NA_action=na_action)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/highlevel.py", line 310, in dmatrices
NA_action, return_type)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/highlevel.py", line 165, in _do_highlevel_design
NA_action)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/highlevel.py", line 70, in _try_incr_builders
NA_action)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/build.py", line 721, in design_matrix_builders
cat_levels_contrasts)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/build.py", line 628, in _make_subterm_infos
default=Treatment)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/contrasts.py", line 602, in code_contrast_matrix
return contrast.code_without_intercept(levels)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/patsy/contrasts.py", line 183, in code_without_intercept
eye = np.eye(len(levels) - 1)
File "/Users/tyler2k/anaconda3/lib/python3.7/site-packages/numpy/lib/twodim_base.py", line 201, in eye
m = zeros((N, M), dtype=dtype, order=order)
ValueError: negative dimensions are not allowed
ANOVA with moderator summary:
An issue with Python has prevented me from adding a moderator so I have attached my ANOVA results without one.
2.1 Chi-square (CODE)
#“libraries”
import pandas
import numpy
import scipy.stats
import seaborn
import matplotlib.pyplot as plt
data = pandas.read_csv('addhealth_pds.csv', low_memory=False)
#print ('Converting variables to numeric’)
data['H1SU1'] = pandas.to_numeric(data['H1SU1'], errors='coerce')
data['H1NB6'] = pandas.to_numeric(data['H1NB6'], errors='coerce')
#print ('Coding missing values’)
data['H1SU1'] = data['H1SU1'].replace(6, numpy.nan)
data['H1SU1'] = data['H1SU1'].replace(9, numpy.nan)
data['H1SU1'] = data['H1SU1'].replace(8, numpy.nan)
data['H1NB6'] = data['H1NB6'].replace(6, numpy.nan)
data['H1NB6'] = data['H1NB6'].replace(8, numpy.nan)
#print ('contingency table of observed counts’)
ct1=pandas.crosstab(data['H1SU1'], data['H1NB6'])
print (ct1)
print ('column percentages')
colsum=ct1.sum(axis=0)
colpct=ct1/colsum
print(colpct)
#print ('chi-square value, p value, expected counts’)
cs1= scipy.stats.chi2_contingency(ct1)
print (cs1)
#print ('set variable types’)
data['H1NB6'] = data['H1NB6'].astype('category')
data['H1SU1'] = pandas.to_numeric(data['H1SU1'], errors='coerce')
seaborn.factorplot(x='H1NB6', y='H1SU1', data=data, kind='bar', ci=None)
plt.xlabel('Happiness Level Living in Neighbourhood 5=Very Happy')
plt.ylabel('Considered Suicide in Past 12 Months')
sub1=data[(data['H1NB5']== 0)]
sub2=data[(data['H1NB5']== 1)]
print ('association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel UNSAFE in it')
# contigency table of observed counts
ct2=pandas.crosstab(sub1['H1NB6'], sub1['H1SU1'])
print (ct2)
print ('column percentages')
colsum=ct1.sum(axis=0)
colpct=ct1/colsum
print(colpct)
print ('chi-square value, p value, expected counts')
cs2= scipy.stats.chi2_contingency(ct2)
print (cs2)
print ('association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel SAFE in it')
# contigency table of observed counts
ct3=pandas.crosstab(sub2['H1NB6'], sub2['H1SU1'])
print (ct3)
print ('column percentages')
colsum=ct1.sum(axis=0)
colpct=ct1/colsum
print(colpct)
print ('chi-square value, p value, expected counts')
cs3= scipy.stats.chi2_contingency(ct3)
print (cs3)
print ('association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel UNSAFE in it')
#print ('set variable types’)
data['H1NB6'] = data['H1NB6'].astype('category')
data['H1SU1'] = pandas.to_numeric(data['H1SU1'], errors='coerce')
seaborn.factorplot(x='H1NB6', y='H1SU1', data=sub1, kind='point', ci=None)
plt.xlabel('Happiness Level Living in Neighbourhood 5=Very Happy')
plt.ylabel('Considered Suicide in Past 12 Months')
print ('association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel SAFE in it')
seaborn.factorplot(x='H1NB6', y='H1SU1', data=sub2, kind='point', ci=None)
plt.xlabel('Happiness Level Living in Neighbourhood 5=Very Happy')
plt.ylabel('Considered Suicide in Past 12 Months')
2.2. Results
H1NB6 1.0 2.0 3.0 4.0 5.0
H1SU1
0.0 138 287 1142 2016 2023
1.0 55 74 227 284 180
column percentages
H1NB6 1.0 2.0 3.0 4.0 5.0
H1SU1
0.0 0.715026 0.795014 0.834186 0.876522 0.918293
1.0 0.284974 0.204986 0.165814 0.123478 0.081707
(122.34711107270866, 1.6837131211401846e-25, 4, array([[ 168.37192655, 314.93401805, 1194.30656707, 2006.50482415,
1921.88266418],
[ 24.62807345, 46.06598195, 174.69343293, 293.49517585,
281.11733582]]))
/Users/tyler2k/anaconda3/lib/python3.7/site-packages/seaborn/categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
warnings.warn(msg)
association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel UNSAFE in it
H1SU1 0.0 1.0
H1NB6
1.0 71 32
2.0 103 29
3.0 192 48
4.0 110 22
5.0 49 8
column percentages
H1NB6 1.0 2.0 3.0 4.0 5.0
H1SU1
0.0 0.715026 0.795014 0.834186 0.876522 0.918293
1.0 0.284974 0.204986 0.165814 0.123478 0.081707
chi-square value, p value, expected counts
(9.694224963778023, 0.04590576662195307, 4, array([[ 81.43825301, 21.56174699],
[104.36746988, 27.63253012],
[189.75903614, 50.24096386],
[104.36746988, 27.63253012],
[ 45.06777108, 11.93222892]]))
association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel SAFE in it
H1SU1 0.0 1.0
H1NB6
1.0 67 23
2.0 184 45
3.0 947 179
4.0 1905 262
5.0 1973 171
column percentages
H1NB6 1.0 2.0 3.0 4.0 5.0
H1SU1
0.0 0.715026 0.795014 0.834186 0.876522 0.918293
1.0 0.284974 0.204986 0.165814 0.123478 0.081707
chi-square value, p value, expected counts
(78.30692095511722, 3.977325608451433e-16, 4, array([[ 79.3676164 , 10.6323836 ],
[ 201.94649062, 27.05350938],
[ 992.97706741, 133.02293259],
[1910.99583044, 256.00416956],
[1890.71299514, 253.28700486]]))
association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel UNSAFE in it
/Users/tyler2k/anaconda3/lib/python3.7/site-packages/seaborn/categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
warnings.warn(msg)
/Users/tyler2k/anaconda3/lib/python3.7/site-packages/seaborn/categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
warnings.warn(msg)
association between Suicidal considerations and respondents level of happiness in their neighbourhood for those who feel SAFE in it
2.3 Chi-Square Summary
For my Chi-square test I looked at analyzing the association between a respondent's level of happiness living in their neighbourhood and if they considered suicide in past 12 months with the moderating variable being whether they feel safe or unsafe in their neighbourhood.
Looking at the association between suicidal considerations and respondents level of happiness in their neighbourhood for those who feel safe in it the p-value is much larger than the threshold which means that I can't accept the null hypothesis. The opposite is true for respondents that feel unsafe in their neighbourhood though it is close to the 0.05 threshold meaning that it might not signify anything.
However, we can also see with the graphs that, at every level, respondents who feel unsafe in their neighbourhood are more likely to have attempted suicide across the board –regardless of how happy they feel in their neighbourhood.
3.1 Pearson Correlation code
import pandas
import numpy
import seaborn
import scipy
import matplotlib.pyplot as plt
data = pandas.read_csv('addhealth_pds.csv', low_memory=False)
"converting variables to numeric"
data["H1SU2"] = data["H1SU2"].convert_objects(convert_numeric=True)
data["H1WP8"] = data["H1WP8"].convert_objects(convert_numeric=True)
data["H1NB6"] = data["H1NB6"].replace(' ', numpy.nan)
"Coding missing values"
data["H1SU2"] = data["H1SU2"].replace(6, numpy.nan)
data["H1SU2"] = data["H1SU2"].replace(7, numpy.nan)
data["H1SU2"] = data["H1SU2"].replace(8, numpy.nan)
data["H1WP8"] = data["H1WP8"].replace(96, numpy.nan)
data["H1WP8"] = data["H1WP8"].replace(97, numpy.nan)
data["H1WP8"] = data["H1WP8"].replace(98, numpy.nan)
data_clean=data.dropna()
print (scipy.stats.pearsonr(data_clean['H1SU2'], data_clean['H1WP8']))
def Nhappy (row):
if row['H1NB6'] <= 2:
return 1
elif row['H1NB6'] <= 3:
return 2
elif row['H1NB6'] >= 4:
return 3
data_clean['Nhappy'] = data_clean.apply (lambda row: Nhappy (row), axis=1)
chk1 = data_clean['Nhappy'].value_counts(sort=False, dropna=False)
print(chk1)
sub1=data_clean[(data_clean['Nhappy']==1)]
sub2=data_clean[(data_clean['Nhappy']==2)]
sub3=data_clean[(data_clean['Nhappy']==3)]
print ('association between number of suicide attempts and parents attendign supper for those who feel UNHAPPY in their neighbourhoods')
print (scipy.stats.pearsonr(sub1['H1SU2'], sub1['H1WP8']))
print ('association between number of suicide attempts and parents attendign supper for those who feel SOMEWHAT HAPPY in their neighbourhoods')
print (scipy.stats.pearsonr(sub2['H1SU2'], sub2['H1WP8']))
print ('association between number of suicide attempts and parents attendign supper for those who feel HAPPY in their neighbourhoods')
print (scipy.stats.pearsonr(sub3['H1SU2'], sub3['H1WP8']))
3.2. Results
runfile('/Users/tyler2k/Downloads/Data Analysis Course/Course 2 - Week 3 - Pearson Correlation', wdir='/Users/tyler2k/Downloads/Data Analysis Course')
/Users/tyler2k/Downloads/Data Analysis Course/Course 2 - Week 3 - Pearson Correlation:18: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects()
For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
data["H1SU2"] = data["H1SU2"].convert_objects(convert_numeric=True)
/Users/tyler2k/Downloads/Data Analysis Course/Course 2 - Week 3 - Pearson Correlation:19: FutureWarning: convert_objects is deprecated. To re-infer data dtypes for object columns, use Series.infer_objects()
For all other conversions use the data-type specific converters pd.to_datetime, pd.to_timedelta and pd.to_numeric.
data["H1WP8"] = data["H1WP8"].convert_objects(convert_numeric=True)
(-0.040373727372780416, 0.25432562116292673)
1 124
2 221
3 454
Name: Nhappy, dtype: int64
association between number of suicide attempts and parents attendign supper for those who feel UNHAPPY in their neighbourhoods
(-0.09190790889552906, 0.30999684453361553)
association between number of suicide attempts and parents attendign supper for those who feel SOMEWHAT HAPPY in their neighbourhoods
(-0.07305378458717826, 0.27955952249152094)
association between number of suicide attempts and parents attendign supper for those who feel HAPPY in their neighbourhoods
(0.009662667237741849, 0.8373203027381138)
/Users/tyler2k/Downloads/Data Analysis Course/Course 2 - Week 3 - Pearson Correlation:43: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
3.3. Summary
For my Pearson correlation test I looked at analyzing an association between the number of suicide attempts and how happy respondents' feel in their neighbourhood organized into 3 categories (unhappy, somewhat happy, and happy) with the moderating variable being the number of meals a week that respondents' parents are present for. I chose this variable as it could be an indication of family cohesiveness and how much time parents are able to devote to spending time with their children.
For the association between number of suicide attempts and parents attending supper for those who feel unhappy and somewhat happy in their neighbourhoods there was a small potential correlation and a much larger potential correlation for those who feel happy in their neighbourhood.
0 notes
Text
Hard Candy (~Misfits AU~)
Chapter 24: Ghost of Christmas Future
Warning: Strong language, implied smut, mention of death and pregnancy, alcohol, if you squint there’s some angst.
(Hard Candy Masterlist)
- Good mornin', roommate - Nathan didn't even have to turn around to know I was there.
- More like good afternoon - I yawned as he turned around and put a grilled cheese in front of me - but after last night I think we both needed some rest, huh?
- Five times is a new record... At least for me - he chuckled.
- Are you meeting us at the bar after work? - I took a bite.
- Yeah, I'll definitely need a drink after that bullshit.
- Well, if it makes you feel any better you look sexy as Santa...
- Actually, it does, but not enough to stop me from wantin' to staple my fingers to a table with a staple gun.
- Don't worry, Natty - I took his hand - I know something good is gonna happen, your life will change.
- Why d’you say that? Am I rich in the future or somethin'? - He mocked.
- Yeah, you all are. I'll never forget the day Simon gave me my first electric guitar, it was a blue Fender Stratocaster with a Hot Rod amp, I had to sell it to buy the time travel...
- Wait, really? We're rich? What did we do? - Nathan jumped, nearly giving me a heart attack.
- I don't know...
- Great! You're a big fuckin' help, Lollipop!
- Nathan!
- Alright, sorry, didn't mean it like that...
Once I finished my brunch, we both got dressed and I dropped Nate off at work like I always do, with a kiss and a thermos filled with hot chocolate.
- I thought you'd be here - I stopped when I saw Simon jumping around the structure of the Community Center.
- Hey, Lyds! - He waved - I've been practicing that double jump I told you about.
- Alright, show me.
Simon waited to get some momentum and ran, first he jumped from one pavilion to the other, then he tried to do another jump and land on the floor, but he slipped and nearly hit a garbage bin. Luckily I was there to ease his fall with a force field, that could've ended up really bad...
- Are you alright? - I held his hand and lowered the mask covering nearly his entire face, a few bruises were already there.
- I'm fine, but I'm still shit at this! Why?
- Cause you only started a couple of months ago, Si, you can't expect to be perfect.
- I bet future Simon was much better than me...
- This makes no sense, you're the same person. Everything that he can do, you can do too. Don't worry, you'll get it.
- Thanks, Peanut - he hugged me tightly.
- Now get back there, I'll protect you if you fall.
I've been missing my orange jumpsuit lately. Of course I'm happy teaching every day and hanging at the bar with the gang, but it just feels so weird to have no adventures, no challenges... After the initial fear that gave me all those nightmares and the anxiety attacks, I hate to admit, it felt like something was missing.
Maybe this wasn't about the missions and the near-death experiences we faced almost every single week for months, maybe this was about what I'm doing with my life. I love to teach, don't get me wrong, but that's not what I wanted to do forever...
- Lydia, can you please tell your brother to stop risking his life like this? - Alisha whined as she handed Simon a plastic bag filled with ice.
- Simon, come on... Let's be more careful, yeah? - I gave him a pointed nod.
- I will try - he assured.
- So bein' Santa sucks a big fat cock - Nathan came in and sat by me, followed by Kelly.
I took the fake beard out of the way and kissed him tenderly. I was so appreciative of everything he's been doing. He doesn't even spend his money on himself at the moment, he just hands me the check every week to help with rent, utilities, and groceries. Needless to say, I feel guilty as fuck because of it.
- Three pints o'lager please - Nathan signed to Alisha.
- Are you gonna pay for them?
- No... - He scoffed as if that was the stupidest thing he's ever heard.
- I got it, Lisha, it's on me - I put the money on the counter.
- Oh, that's why I love you - Nathan rubbed circles on the back of my hand - I gotta find a better job though.
- Yeah, me too - I said without thinking about it.
- What? Your job's perfect, you work from home, only a few hours a day, and doin' what you love, what's there not to like? - Kelly asked.
- Nothing, I don't know why I said that...
Alisha gave each one of us a pint, I was about to take my first swig when Curtis came in and started freaking out:
- No more free drinks! - He scolded.
Nathan was so used to having Curtis complain about that, he instinctively started chugging his beer as fast as he could.
- Come on, I paid for them - I huffed.
- Such a prick... - Curtis rolled his eyes at Nathan.
Alisha and Kelly grimaced while Simon and I laughed at Nate's stupid stunt. He slammed the cup on the counter and belched obnoxiously before turning to wink at me, and I shook my head with a smile:
- So, what d'you reckon, Lollipop?
- Eight, you can do better - I shrugged and Kelly groaned in disgust.
- Let's see about that, refill - Nathan gave Curtis the glass.
- You're gonna get us both sacked...
- You really wanna spend the rest o'your life workin' in some shitty bar?
- No.
- Then I'm doin' you a favor.
Before Curtis could counter-argument, Nikki came marching in, cursing under her breath.
- Fucking ridiculous! I had to walk all the way back from the other side of the Estate...
- Are you okay? - Curtis held her hands.
- Yeah... My knickers - she muttered.
Nathan turned to me agape and elbowed my arm with a childish giggle. I felt a little bad for Nikki, if I was having sex with Nate and teleported out of nowhere I would be pissed off, especially if I had to walk all the way back with no knickers on...
——————————————————-
- Hey, Nats, I'll be right there with you, I need to take this, it's a student - I looked at my phone screen.
- Alright - Nathan gave me a peck on the lips and walked into the Community Center.
I picked up the phone as Nathan was dropping off his costume so we could go home.
One of my students had an audition next week, so we would need an extra lesson, not a problem... But when I walked through the door, my day, which was going pretty well so far, was ruined. Absolutely ruined, smashed, and shat on.
- This is my girlfriend, Lydia - Nathan pulled me closer.
- Girlfriend? You have a girlfriend? - She asked, both hands resting on her huge pregnancy bump.
- Lyds, this is Marnie.
- I know - I felt like I was about to faint.
- Are you ok, baby? You look like you've seen a ghost - Nate whispered.
- It's her - I whispered back.
- Her who?
- Your ex future wife, that's her...
- Oh? - He looked at me puzzled - You sure? She's not really my type.
- Well, where I come from the two of you get married in a year and this baby calls you dad...
- Is everything ok? - Marnie asked with her child-like innocence that I hated so much.
- Yeah, yeah... Brilliant, just gonna drop off my costume and go home, y'know? The flat I share with my serious, exclusive girlfriend who I love very much - Nathan ran to the locker room like lightning.
- Is he always like this?
- Yeah... That's why I fell in love with him - I started biting my nails, I finally managed to stop, but damn it, I was nervous!
- I see what you mean, I like that type of guy too, your boyfriend's very cute.
- I'm sure you'll find one for yourself... One that likes babies and isn't taken - I had no reason to hate her, right? She did nothing wrong, but every time I see her it's like this deep-seated loathing takes over my brain.
- I hope so... He doesn't happen to have any brothers does he?
- Um, no. Unfortunately, his only brother passed away a while back
- Hey - Nathan came back and made a show of putting his arm around my waist - so, let's go?
- Yeah, see you around - I waved as we left, hoping we never see her again.
The walk home was pretty much silent, I kept thinking about their wedding day, how happy they were. Truth is, she wasn't a bad person, she didn't make his life miserable, so there was always this little voice in the back of my head saying "maybe he'd be happier with her, maybe he'd love her more".
- Pregnant? So I guess I dodged a bullet there - Nathan locked the door after we walked in.
- Yeah - I sat on the couch and turned on the TV.
- I feel like I should thank you.
- No problem.
- So, what d'you want for dinner? We have frozen pizza, chicken nuggets, leftover lasagna, I can make a few sandwiches... - Nathan moved to the fridge.
- Don't know.
- What d'you fancy, baby?
- Pick whatever.
Nathan thought for a second about the best course of action and closed the fridge with a smirk.
He walked over to the couch and started kissing my neck very teasingly, using his leg to spread mine, one hand under my shirt, groping my breast.
- I think I know what's your deal - he drawled - you want dessert before dinner don'tcha? My little tart...
- No - I didn't move, I don't think I've ever actually not been in the mood before.
- Don't you want me to shag you? - He pulled away, trying to decipher the look on my face.
- Not now.
- Alright, seems like you're upset, wanna talk about it? - He sat by my side.
- Not really.
- I wanna help you, Lyddie, but you need to say more than two words. Tell me what's cloggin' your heart so I can unclog it and make you feel better, that's one o'my only talents.
- It's nothing.
- D'you want me to just hold you?
- Please...
Nathan pulled me on top of him and embraced me, pressing my head against his chest and leaving kisses all over my face.
- Is that better?
- Much better - my voice trembled from the tears I was trying to hold back.
- What d'you say... I'll hold you for a little while, then I'll heat up some lasagna, and we can watch any movie you want? Maybe Hairspray, you love that one.
- Alright, I guess it sounds good.
- Thank God! Finally a full sentence!
——————————————————-
I was a little bit better next morning, but I still wasn't able to talk to Nathan about the way I felt. I was too scared of him actually thinking about it and realizing this whole thing between us was a mistake.
- How can you still have shit scattered around this place after three months? - I mumbled as we walked into the Community Center.
- Are you angry with me? - Nathan asked quietly.
- No, why would I be? You did nothing wrong.
- I feel like you are...
- I'm not, Nats, really, I just want Christmas to be over.
- Not a fan?
- I hate it! All the families pretending to love each other, capitalism, the stupid weather... Remembering you with her hurts me so much I'm scared you're gonna leave me because you never truly loved me I'm just a stupid 12-year-old who thirsts over you in the bowling alley - this last part came out all in one breath unleashing a waterfall of tears as well.
- There it is - Nathan kissed me and gave me a long hug - now that you got all this rubbish out, you'll feel better.
- Are you with me just ‘cause you're guilty?
- Guilty? What d'you mean?
- That I came all this way to be with you so you feel like you need to be with me.
- No! No, Lyddie, I love you. I wanna be with you, I already wanted it before I even knew about the whole time travel thing.
- Are you sure you don't wanna be with her?
- Lyds, what did I say t'you when we kissed in the future?
- You said it was a right person wrong time situation.
- When I said that, I know meant it. You're the right person, I've never seen two people so right for each other. I'm sure she's lovely, but she's not you. Plus if I left you, I'd be homeless again...
- Wanker! - I punched his chest with a laugh.
- Lyds? - I heard Simon's voice - Nathan?
- Look, Barry's here! - Nathan cheered - He can help you feel better, right?
- What's he doing here?
- I don't know... Destiny? Or maybe you have this crazy brother-sister connection and he felt like you needed him.
- What's wrong? Your text said it was urgent - Simon finally found us.
I looked at Nate, who had a sheepish smile on. It was kinda sweet that he asked Si for help.
- I'll give you two some time alone while I gather my things - Nathan tapped my shoulder before walking to the locker room.
- Did he do something to you? - Simon wiped away my tears with his thumb.
- No, it's just... We bumped into his ex future wife yesterday and I can't stop thinking about them together.
- Nathan would have to be very stupid to leave you, not even he's that dumb. That prick loves you, Peanut. I hate to admit it, because that twat is the last man mom and dad imagined for you, but you were made for each other.
- I just think maybe he would be happier with her.
- If he was so happy with her, why did he fall in love with you in the future?
- I guess you have a point...
Nathan came out with a tiny plastic bag and sat by us.
- So, how's the little family therapy goin'?
- Great - I rested my head on Nathan's shoulder.
- Well, since we're already here... - Simon sighed - Something happened yesterday, Alisha got rid of her power.
- What? - I shouted - How did she do that?
- You know those "cash for powers" posters around town? She went to that guy and he took it away.
- How much did she get for it? - Nathan asked.
- Nothing, she just wanted it gone.
- Well, that's bollocks! If she didn't want money she could've given it to me! How much you think they would pay for mine?
- No, don't even think about it, Nathan! - I scolded - There's no fucking way!
- But Lyds... If I sell it, I can quit this stupid job and actually pull my weight around the house.
- Don't be ridiculous, I've seen you die more times than I can count. I have no idea how you survived two decades without this power. Sell it when we're both 90 and ready to go.
- But, darlin'...
- Listen to the brains of this relationship, Nats.
- Alright, fair enough.
- Alisha and I had sex - Simon's voice was nearly a whisper.
- Ooooh... - I giggled - Wait, why do you sound so upset?
- I was shit.
- Oh, so you're after some sex tips from a far more experienced lover - Nathan said, all cocky - two words: Fisherman's Friend.
- Ah, yeah! Listen to this one, Si, it's amazing! - I got goosebumps just from the mention of it.
- Isn't that a cough sweet? - Simon seemed confused.
- You pop one o'those bad boys in your mouth and then you head due south and you pleasure her, orally... It's the menthol, she's gonna feel like her pussy's on fire! - Nathan looked at me with a shit-eating smirk - Lemme tell you, man, when I do it to Lyddie, she goes mad. Pretty sure all the neighbors hate me, but who cares? I always keep some on me in case this Lollipop needs lickin'. Here, you can have it.
- Ew, I’m not gonna ask why there’s only a couple left... But thanks - Simon grabbed the packet from Nathan.
- Ask her what she likes - I added - each woman likes it a different way, if you practice you'll get better.
- Right - Nathan snapped his fingers - try to find out if she has fetishes or somethin', you've got no idea what a good teasin' can do. Learn how to read her signs, like right now: Lyddie is proper horny, I can tell, d'you see how she's crossin' her legs like this? Arms folded to cover her chest? That's 'cause she's...
- I think that's enough - Simon got up.
——————————————————-
- I'm about to change your lives! Today, right now! - A man shouted while standing on one of the patio tables.
- Check that out - I stopped to watch the lunatic.
- What's all this? - Nathan nudged a girl's arm.
- Our Lord Jesus Christ has risen again - she stared at him in awe.
- Right... Good for him - Nate draped his arm around me and we left for the bar - can you believe this, Lyddie?
- I hope he invites us to the birthday party...
As soon as we walked into the bar, I ran to hug Alisha. I made it a point to touch every last bit of her exposed skin.
- So, I guess Simon told you... - She laughed.
- Yeah, I never thought I'd be able to do that again! - I held her hands for the very first time in that timeline.
- Have you been cryin'? - Kelly turned my face to her, probably intrigued by my puffy red eyes.
- Just a little...
- The whole waterworks - Nathan tried to take Alisha's hand, but she slapped him away - this one had a case of too-much-shit-in-the-brain syndrome.
- What happened? - Alisha asked.
- Wait, let me guess - Nikki held her finger up - your boyfriend took a shit on your bed?
- You need to get over this - Nathan shook his head.
- It wouldn't be such a wild guess - Curtis joked.
- I wish that was it - I scoffed - we bumped into Marnie, Nathan's future wife in the original timeline.
- Did Nathan do somethin' stupid with this girl? - Kelly gave him a death glare, ready to hit him if necessary.
- No! - He put both hands up - I barely spoke t’her and I didn't know! I just said she shouldn't smoke while pregnant, I told her I had a girlfriend and all...
- Well, in that case - Alisha served each one of us a beer - there's nothing to worry about.
- Yeah, I know, I just have all those memories, it's hard not to think of it - I traced the edge of my glass with my finger, while Nathan was halfway through his.
- I think I speak for all of us when I say... Fuck Marnie! - Kelly raised her glass.
- Fuck Marnie! - Everyone did the same and I couldn't keep from smiling, that was the sweetest thing ever.
- Just figuratively - Nathan clarified - 'cause I definitely won't be doin' that.
When my phone started ringing I thought it would another one of my students asking for help, but I didn't recognize the number...
- Hello? - I picked up - Yeah, it's me, but how do you know that? A video... No, we can meet. Can I text you my e-mail instead? Sure, tomorrow's good, I'll see you then. Goodbye.
- Who was it? - Simon broke the silence.
- A record label - I was in shock - a producer wants to meet me because someone sent them the video you made of me singing on the rooftop.
- Oh, yeah - Kelly smiled - I forgot to tell ya, I sent it a couple months ago to loads of different places.
- Jesus! Kelly, those aren't even my songs...
- We talked about that, you can actually get famous, you've got so much talent.
- That's awesome! I've always wanted to shag a rockstar... - Nathan waggled his brows.
- Well, I'm meeting them tomorrow, and I'm taking the songs with me, but I need to establish rules... I won't take first hits, I won't steal from independent artists, no one-hit wonders, absolutely no songs from musicals and no songs from Panic! At The Disco - I took notes on a napkin as I said it.
- Sounds good - Curtis agreed - I think this calls for another toast then!
After many toasts, Nathan and I were just slightly buzzed, but not really drunk. That sweet spot where things are funny and beautiful, but you don't feel sick or dizzy.
- I'm so proud, Lollipop - he cupped my face firmly while we laid down in bed.
- You're gonna make me blush.
- I hope so, you look adorable when you blush... - His eyes were darkening as he wet his lips - So how 'bout I prove to ya that I've only got eyes for one girl? My beautiful, sexy, gorgeous Lydia.
- Do you have Fisherman's Friend? - A cheeky grin tugging at my lips - I've been craving it since you brought it up.
- I noticed...
Without letting go of me, he reached for the nightstand as his mouth crashed with mine. His tongue so eager in that urgent, hungry kiss.
- I'm all yours - Nathan murmured against my lips - every last bit, it's all for you.
- I like the sound of that...
- Before I pop one o'these - Nathan put the candy to the side - I've been thinkin', you deserve a treat.
- What? - I bit my lip.
- That thing you don't let me say...
- Lately you've been doing that all the time - I giggled.
- Yeah, cause I like to see your face when you're tryin' to hide that you're turned on, but I'll do it really special tonight, put on a little show for ya.
- Well, you have my attention.
#misfits#misfits nathan#misfits fanfic#misfits imagine#misfits tv#imagine#fanfic#nathan young#nathan young x oc#oc#hard candy#multichapter
24 notes
·
View notes