Welcome, Guest: Register On Nairaland / LOGIN! / Trending / Recent / New
Stats: 3,153,229 members, 7,818,773 topics. Date: Monday, 06 May 2024 at 02:28 AM

Chronicle Of A Data Scientist/analyst - Programming (89) - Nairaland

Nairaland Forum / Science/Technology / Programming / Chronicle Of A Data Scientist/analyst (331863 Views)

Chronicle Of A Data/cloud Engineer / Net Salary For A Data Analyst Or Scientist Or Web Dev / Aspiring Data Scientist. (2) (3) (4)

(1) (2) (3) ... (86) (87) (88) (89) (90) (91) (92) ... (146) (Reply) (Go Down)

Re: Chronicle Of A Data Scientist/analyst by hexzelle: 11:10pm On Mar 27, 2021
.
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 11:28pm On Mar 27, 2021
.
Re: Chronicle Of A Data Scientist/analyst by lovelybobo: 3:48am On Mar 28, 2021
hexzelle:

i'm not sure if that pix is clear
so i have uploaded the file also attached

if one opens that file in excel, there are about 25 number sets there , if one observes carefully one would find out that each set contains a number between(30-32=100%) , i.e all 25 sets have either 30, 31, or 32
while 24 sets contains between (20-22=95%).
and also 24 sets contain between(21-23=95%).
all three are a range of 3 numbers.

but also all 25 contain(20-23=100%) which is a range of 4 numbers i.e 20, 21,22,23

my question now is if there is a function on excel or another software, where i can enter different sets like this, and choose either a 2 NO range, 3 NO range or 4 NO range and then it would give me the range of numbers that is present in all the sets i.e (100%) or a percentage basis of the ranges automatically.

If I understand your question clearly, In Microsoft Excel you can solve the problem using IFS or Nested IF depending on the version of Microsoft Excel you are using.
All the best
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 11:49am On Mar 28, 2021
lovelybobo:


If I understand your question clearly, In Microsoft Excel you can solve the problem using IFS or Nested IF depending on the version of Microsoft Excel you are using.
All the best

THANKS for your response, i have re-edited it for more clarity

to your suggestion, wouldn't the function IF treat the whole "25 DATA SETS" as one singular data?
Re: Chronicle Of A Data Scientist/analyst by opkomo(m): 5:38pm On Mar 28, 2021
Please am also interested, can you share it to me on dis e-mail:johnchukwunenyenwa@gmail.com
Re: Chronicle Of A Data Scientist/analyst by opkomo(m): 5:43pm On Mar 28, 2021
[quote author=Edintee post=93353787]

Please bros am also interested, send it to me through here: johnchukwunenyenwa@gmail.com
Re: Chronicle Of A Data Scientist/analyst by Singingbae(m): 10:43am On Mar 30, 2021
Guys, please I have issues visualizing my data. It says “value error: x and y must be same size”. Please I need help on how to solve this. It’s really stressing me out.
Note: I’ve tried the .reshape(-1,1) and getting another error like, expected a 2D array, got 1D instead.

I have the google colab link here https://colab.research.google.com/drive/1mQEpInsPMW_Blz5DPAWpbZGVqjwZxVW5?usp=sharing

I don’t mind to drop my WhatsApp number so we can discuss more. This is stopping me from moving forward on the project
Re: Chronicle Of A Data Scientist/analyst by tplayer: 2:46am On Mar 31, 2021
hexzelle:

i'm not sure if that pix is clear
so i have uploaded the file also attached

if one opens that file in excel, there are about 25 number sets there , if one observes carefully one would find out that each set contains a number between(30-32=100%) ORANGE, i.e all 25 sets have either 30, 31, or 32
while 24 sets contains between (20-22=95%) ONLY COLORED LITE BLUE.
and also 24 sets contain between(21-23=95%)DARK BLUE.
all three are a range of 3 numbers.

but also all 25 contain(20-23=100%) which is a range of 4 numbers i.e 20, 21,22,23

my question now is if there is a function on excel or another software, where i can enter different sets like this, and choose either a 2 NO range, 3 NO range or 4 NO range and then it would give me the range of numbers that is present in all the sets i.e (100%) or a percentage basis of the ranges automatically.

@mbhs139
@Sirwallace
@Marveaux
@Ejiod


You essentially want to color cells based on individual values contained within them, abi. Example: 30-32 (ORANGE), 20-22(BLUE), 21-23(DARK BLUE), and 20-23(another colour), abi.
Then, enter 1 to get ORANGE cells, 2 to get BLUE blue , 3 for DARK BLUE cells, and 4 for another colour cells, abi

If yes, use conditional formatting sharp.
Re: Chronicle Of A Data Scientist/analyst by dauddy97(m): 10:17pm On Mar 31, 2021
Singingbae:
Guys, please I have issues visualizing my data. It says “value error: x and y must be same size”. Please I need help on how to solve this. It’s really stressing me out.
Note: I’ve tried the .reshape(-1,1) and getting another error like, expected a 2D array, got 1D instead.

I have the google colab link here https://colab.research.google.com/drive/1mQEpInsPMW_Blz5DPAWpbZGVqjwZxVW5?usp=sharing

I don’t mind to drop my WhatsApp number so we can discuss more. This is stopping me from moving forward on the project

I checked your Colab and I saw the great work you have been doing. well done.
I also tried running your chat, scatter plot.
pls try this using pandas.

df.plot.scatter(x='length', ... y='width', ... c='DarkBlue')

Did I answer your question?

1 Like

Re: Chronicle Of A Data Scientist/analyst by Singingbae(m): 9:39pm On Apr 01, 2021
dauddy97:


I checked your Colab and I saw the great work you have been doing. well done.
I also tried running your chat, scatter plot.
pls try this using pandas.

df.plot.scatter(x='length', ... y='width', ... c='DarkBlue')

Did I answer your question?
Thanks I got it already but I’ll also need you to check the latest goggle colab I did and see if the visualization is really that of a linear regression!
https://colab.research.google.com/drive/1mQEpInsPMW_Blz5DPAWpbZGVqjwZxVW5#scrollTo=oqqIxy3KDmMN
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 11:38pm On Apr 01, 2021
tplayer:


You essentially want to color cells based on individual values contained within them, abi. Example: 30-32 (ORANGE), 20-22(BLUE), 21-23(DARK BLUE), and 20-23(another colour), abi.
Then, enter 1 to get ORANGE cells, 2 to get BLUE blue , 3 for DARK BLUE cells, and 4 for another colour cells, abi

If yes, use conditional formatting sharp.

i used conditional formatting to get those colors on the image, but it was a manual process, i want to have it automated.

but i doubt excel automates functions.
Re: Chronicle Of A Data Scientist/analyst by Marveaux(m): 5:24am On Apr 02, 2021
hexzelle:


i used conditional formatting to get those colors on the image, but it was a manual process, i want to have it automated.

but i doubt excel automates functions.
Would have loved to help, but I'm honestly still trying to wrap my head around your question.
Re: Chronicle Of A Data Scientist/analyst by Marveaux(m): 6:34am On Apr 02, 2021
Singingbae:

Thanks I got it already but I’ll also need you to check the latest goggle colab I did and see if the visualization is really that of a linear regression!
https://colab.research.google.com/drive/1mQEpInsPMW_Blz5DPAWpbZGVqjwZxVW5#scrollTo=oqqIxy3KDmMN
Most times for me (might be different for you) I try to visualize the data first before carrying out any predictive analysis. It can help to tell you what type of algorithm to use((linear,polynomial) regression e.t.c).
From your data(which in my opinion is quite sparse,a lot of 0s), I don't think you should be plotting the x against y or vice versa since it's a scatter plot, rather reduce the dimensions (PCA) to say 2 components and then plot the two components against each other.
plt.scatter(component_1, component_2).
Note: sometimes the visualization won't really tell you anything i.e if it's linear or something else.
Hope I helped,Cheers.
Re: Chronicle Of A Data Scientist/analyst by tplayer: 8:14am On Apr 02, 2021
hexzelle:


i used conditional formatting to get those colors on the image, but it was a manual process, i want to have it automated.

but i doubt excel automates functions.

VBA is the answer!
It's not a difficult language. If you already have programming experience, you can be productive with it in weeks.
Re: Chronicle Of A Data Scientist/analyst by Singingbae(m): 8:51am On Apr 02, 2021
Marveaux:

Most times for me (might be different for you) I try to visualize the data first before carrying out any predictive analysis. It can help to tell you what type of algorithm to use((linear,polynomial) regression e.t.c).
From your data(which in my opinion is quite sparse,a lot of 0s), I don't think you should be plotting the x against y or vice versa since it's a scatter plot, rather reduce the dimensions (PCA) to say 2 components and then plot the two components against each other.
plt.scatter(component_1, component_2).
Note: sometimes the visualization won't really tell you anything i.e if it's linear or something else.
Hope I helped,Cheers.
Thank you so much, but the 0s are as a result of the category columns getting dummied. Thanks, I’ll try to reduce to two components, please when is it best to use a regression! I don’t mind you explain to me in detail
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 3:01pm On Apr 02, 2021
.
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 3:34pm On Apr 02, 2021
tplayer:


VBA is the answer!
It's not a difficult language. If you already have programming experience, you can be productive with it in weeks.

THANKS for your contribution, i think it might offer some help, but i don't know much about it, wondering if you do ?
if you can, i could use your assistance, which i don't expect to be free

THANKS ONCE AGAIN.
Re: Chronicle Of A Data Scientist/analyst by tplayer: 4:40pm On Apr 02, 2021
hexzelle:


THANKS for your contribution, i think it might offer some help, but i don't know much about it, wondering if you do ?
if you can, i could use your assistance, which i don't expect to be free

THANKS ONCE AGAIN.

Sorry, as I am just improving/rebrushing up my VBA skills
But if you want a situation where you input 1 or 2 or 3 or whatever number in a particular cell and something happens, you can still use conditional formatting ooo.
If you are not time-barred, ask me in 4 weeks time if you want complete automation by VBA
Re: Chronicle Of A Data Scientist/analyst by hexzelle: 9:40am On Apr 03, 2021
tplayer:


Sorry, as I am just improving/rebrushing up my VBA skills
But if you want a situation where you input 1 or 2 or 3 or whatever number in a particular cell and something happens, you can still use conditional formatting ooo.
If you are not time-barred, ask me in 4 weeks time if you want complete automation by VBA

thanks for your honesty!
Re: Chronicle Of A Data Scientist/analyst by Singingbae(m): 12:05am On Apr 04, 2021
Marveaux:

Most times for me (might be different for you) I try to visualize the data first before carrying out any predictive analysis. It can help to tell you what type of algorithm to use((linear,polynomial) regression e.t.c).
From your data(which in my opinion is quite sparse,a lot of 0s), I don't think you should be plotting the x against y or vice versa since it's a scatter plot, rather reduce the dimensions (PCA) to say 2 components and then plot the two components against each other.
plt.scatter(component_1, component_2).
Note: sometimes the visualization won't really tell you anything i.e if it's linear or something else.
Hope I helped,Cheers.
Bro, thanks and I also come up with a better way you can view my code. I’ll be dropping a google repository link for you and I want you to help me comment, is the graph am getting good for a linear regression graph? What can I work on to make the graph a “normal” linear graph
NOTE: I ran polynomial regression in the same x and y, I got the same graph. Down is the link
https://github.com/adedokun44/How-median-income-and-ocean-proximity-to-house-affects-house-values/blob/main/housing_value_prediction_github.ipynb
Thanks in anticipation. I wish everyone can check the link out please

1 Like 1 Share

Re: Chronicle Of A Data Scientist/analyst by SuperKlean(m): 10:47pm On Apr 08, 2021
wisdomremz:
already started my journey into data science, prior before now I had a mentor(my cousin) who is a data scientist in Australia who talked extensively on data science and gave various tools necessary. So I brushed through excel by taking some course like analysing data using excel and other courses on Edx(videos) then currently learning sql using sql server express learnt basics using w3schools and sqlzoo which am done, practicing using ssms and sample database like(adventureworks and northwind) so refreshing. Also [b]I have some PDFs book having questions and problem [/b]from beginner to advance on the sample database listed, once am done I will also take some courses on edX. Afterwards would move into python and other tools.


just wanted to share my journey for the past one month. thanks Ejiod and other contributors.

if you are also on this journey into the world of data science quote me, let's relate �
hello, please can I get the file from you?
Re: Chronicle Of A Data Scientist/analyst by SuperKlean(m): 10:48pm On Apr 08, 2021
wisdomremz:
already started my journey into data science, prior before now I had a mentor(my cousin) who is a data scientist in Australia who talked extensively on data science and gave various tools necessary. So I brushed through excel by taking some course like analysing data using excel and other courses on Edx(videos) then currently learning sql using sql server express learnt basics using w3schools and sqlzoo which am done, practicing using ssms and sample database like(adventureworks and northwind) so refreshing. Also I have some PDFs book having questions and problem from beginner to advance on the sample database listed, once am done I will also take some courses on edX. Afterwards would move into python and other tools.


just wanted to share my journey for the past one month. thanks Ejiod and other contributors.

if you are also on this journey into the world of data science quote me, let's relate �
hello, please can I get the file from you?
Re: Chronicle Of A Data Scientist/analyst by Lordsagna: 8:21pm On Apr 09, 2021
I'm having issue installing MySQL.. pls can someone help me?
Re: Chronicle Of A Data Scientist/analyst by SuperKlean(m): 5:11pm On Apr 10, 2021
mcemmy0z:
If you reside around songo Ota I have these available
*Udemy - Beginner to Pro in Excel Financial Modeling and Valuation
*Udemy - SQL - MySQL for Data Analytics and Business Intelligence
*Tableau 10 A-Z Hands-On Tableau Training For Data Science!
*Tableau Hands-on Learn Data Visualization with Tableau
*Udemy - Power BI A-Z Hands-On Power BI Training For Data Science
*Udemy - Machine Learning A-Z™ Hands-On Python & R In Data Science
*Udemy - Python for Financial Analysis and Algorithmic Trading
hello bro, please how can I contact you?
Re: Chronicle Of A Data Scientist/analyst by psalmsonovic(m): 10:59am On Apr 11, 2021
I am having issues installing mysql
Re: Chronicle Of A Data Scientist/analyst by mcemmy0z: 5:25pm On Apr 11, 2021
SuperKlean:
hello bro, please how can I contact you?
PM me
Re: Chronicle Of A Data Scientist/analyst by Mrves111: 7:06pm On Apr 11, 2021
Happy Sunday guys, please I want to know which book is suitable for someone that want to learn hadoop as a beginner. I will really appreciate any link to the free book that will be every resourceful. Thanks guys
Re: Chronicle Of A Data Scientist/analyst by Mrves111: 1:12pm On Apr 12, 2021
Mrves111:
Happy Sunday guys, please I want to know which book is suitable for someone that want to learn hadoop as a beginner. I will really appreciate any link to the free book that will be every resourceful. Thanks guys

Hello guys, please I need your assistance
Re: Chronicle Of A Data Scientist/analyst by dauddy97(m): 10:55pm On Apr 13, 2021
Mrves111:


Hello guys, please I need your assistance
i bought a book recently on Hadoop. it very interesting and practically intensive. i will give you for few $$. It's not compulsory Sir.
Re: Chronicle Of A Data Scientist/analyst by elvisgaga: 2:58pm On Apr 14, 2021
which site that is text based best for power bi tutorial and where can I download raw data from? eg countries populatio 1950 - 1999
Re: Chronicle Of A Data Scientist/analyst by Mrves111: 8:05am On Apr 18, 2021
dauddy97:

i bought a book recently on Hadoop. it very interesting and practically intensive. i will give you for few $$. It's not compulsory Sir.


I'm interested Sir, can we chat privately because I need the book urgently

(1) (2) (3) ... (86) (87) (88) (89) (90) (91) (92) ... (146) (Reply)

I Want To Learn Programming. Which Language Should I Start With?

(Go Up)

Sections: politics (1) business autos (1) jobs (1) career education (1) romance computers phones travel sports fashion health
religion celebs tv-movies music-radio literature webmasters programming techmarket

Links: (1) (2) (3) (4) (5) (6) (7) (8) (9) (10)

Nairaland - Copyright © 2005 - 2024 Oluwaseun Osewa. All rights reserved. See How To Advertise. 44
Disclaimer: Every Nairaland member is solely responsible for anything that he/she posts or uploads on Nairaland.