SlideShare a Scribd company logo
1 of 19
TITLE
PRODUCTIVITY PREDICTION OF
GARMENT EMPLOYEES
Under the guidance of:
Mrs.G.Vijaya Laxmi(Associative Professor)
Miss.J.Madhavi(Assistant Professor)
Department of Computer Science and Engineering in Artificial Intelligence and Machine Learning (CSE – AI & ML)
TEAM MEMBERS
D.Sharvani(20641A6610)
A.Archana(20641A6638)
K.Akhil(20641A6618)
B.Anirudh Reddy(20641A6622)
Introduction
 The Garment Industry is one of the key examples of the
industrial globalization of this modern era. It is a highly
labor-intensive industry with lots of manual processes.
 Satisfying the huge global demand for garment products is
mostly dependent on the production and delivery
performance of the employees in the garment
manufacturing companies.
 So, it is highly desirable among the decision-makers in the
garments industry to track, analyze, and predict the
productivity performance of the working teams in their
factories.
3
Abstract
 The garment industry is one of the key examples of the
industrial globalization of this modern era. It is a highly labor-
intensive industry with lots of manual processes. Satisfying the
huge global demand for garment products is mostly dependent
on the production and delivery performance of the employees in
the garment manufacturing companies.
 So, it is highly desirable among the garment industry decision-
makers to track, analyze, and predict the productivity
performance of the working teams in their factories. This study
explores the application of state-of-the-art data mining
techniques for analyzing industrial data, revealing meaningful
insights, and predicting the productivity performance of the
working teams in a garment company.
 We have applied eight different data mining techniques with six
evaluation metrics as part of our exploration.
4
Existing Systems
 Raw-Material Issue. Raw materials are
essential to the garment industry
 Inventory Management Issue
 Production Delays
 Order Processing Issue
 Garment Defects
5
Proposed Systems
 If you are working in garment production or planning to open your
own garment company, you would need an all-in-one solution that
can help you to solve these challenges and issues and improve your
business productivity and performance. Garments ERP management
software is designed to help you overcome these operational
challenges. From planning, manufacturing, and order processing to
distribution, this robust software can easily handle all your
operational tasks and distribution activities.
 All manufacturing industries deal with various challenges and issues
in their product manufacturing processes. That is why today we will
discuss five common problems that all garment manufacturers face
that hamper their product quality and production performance.
6
MERITS AND DEMERITS
MERITS
It is used to reduce work
pressure of an employee.
It helps in saving raw
materials.
It is used as a guide for those
who are starting new garment
industries.
By using this we can save
money.
It will help an industries to
gain profits.
DEMERITS
Retraining is not possible in
Machine Learning.
The data we give for training
should me accurate otherwise
the result will be incorrect.
20XX presentation title 7
ALGORITHMS USED
K-Nearest Neighbors
algorithm
Linear Regression
Support Vector Machine
Decision Tree Using
Regression
Random Forest
20XX presentation title 8
9
Flow Chart
Requirements
Hardware Requirements
 RAM(8GB)
 ROM(64 bitprocessor)
 Windows 10
 HARD DISK 256GB
 I5 PROCESSOR
Software Requirements
 Python
 Python 3
 Libraries
 NumPy
 OpenCV, etc
10
Code
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import sklearn
df = pd.read_csv('/content/drive/MyDrive/garments_worker_productivity.csv')
df.head()
df.shape
df.describe()
df2 = df.drop(['date', 'day'], axis=1)
df2.shape
df3 = df2.fillna({'wip': 0,})
df3.isnull().sum()
plt.figure(figsize=(10,5))
p = sns.boxplot(data = df3, orient ='v',width=0.8)
plt.xticks(rotation=90)
Q1 = df3.incentive.quantile(0.25)
Q3 = df3.incentive.quantile(0.75)
Q1, Q3
11
IQR = Q3 - Q1
IQR
lower_limit = Q1 - 1.5*IQR
upper_limit = Q3 + 1.5*IQR
lower_limit, upper_limit
df3[(df3.incentive<lower_limit)|(df3.incentive>upper_limit)]
df4 = df3[(df3.incentive>lower_limit)&(df3.incentive<upper_limit)]
df4.shape
Q1 = df4.wip.quantile(0.25)
Q3 = df4.wip.quantile(0.75)
Q1, Q3
IQR = Q3 - Q1
IQR
lower_limit = Q1 - 1.5*IQR
upper_limit = Q3 + 1.5*IQR
lower_limit, upper_limit
df4[(df4.wip<lower_limit)|(df4.wip>upper_limit)]
df5 = df4[(df4.wip>lower_limit)&(df4.wip<upper_limit)]
df5.shape
Q1 = df5.over_time.quantile(0.25)
Q3 = df5.over_time.quantile(0.75)
Q1, Q3
IQR = Q3 - Q1
IQR
lower_limit = Q1 - 1.5*IQR
12
upper_limit = Q3 + 1.5*IQR
lower_limit, upper_limit
df5[(df5.over_time<lower_limit)|(df5.over_time>upper_limit)]
df6 = df5[(df5.over_time>lower_limit)&(df5.over_time<upper_limit)]
df6.shape
lt.figure(figsize=(10,5))
p = sns.boxplot(data = df6, orient ='v',width=0.8)
plt.xticks(rotation=90)
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
for i in range(0, df6.shape[1]):
if df6.dtypes[i]=='object':
df6[df6.columns[i]] = le.fit_transform(df6[df6.columns[i]])
x = df6.drop(['actual_productivity'], axis=1)
y = df6.actual_productivity
x.shape, y.shape
y.head()
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
x.iloc[:,:] = scaler.fit_transform(x.iloc[:,:])
x.head()
sns.pairplot(df,hue = "team")
plt.figure(figsize=(12, 10))
sns.heatmap(df6.corr(), annot=True,vmin=-1,vmax=1,cmap='viridis',square=True)
13
df.iloc[:, 1:].plot.density(subplots=True, layout=(1,11), figsize=(20, 10), sharex = False)
df_wip = df[df.wip > 0]
sns.barplot(x="day", y="wip", data=df_wip)
df_diff = df["actual_productivity"] - df["targeted_productivity"]
sns.lineplot(x = df["date"], y = df_diff, ci = None)
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.30, random_state=42)
print(x_train.shape)
print(x_test.shape)
print(y_train.shape)
print(y_test.shape)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_axes([0,0,1,1])
algo = ['Linear regression','knr','SVr','Descision Tree','Random Forest']
accuracy = [linreg.score(x,y),knn.score(x,y),svr.score(x,y),dt.score(x,y),randf.score(x,y)]
ax.bar(algo[0],accuracy[0],color = 'g')
ax.bar(algo[1],accuracy[1],color = 'b')
ax.bar(algo[2],accuracy[2],color = 'y')
ax.bar(algo[3],accuracy[3],color = 'r')
ax.bar(algo[4],accuracy[4],color = 'y')
plt.xlabel('Classifiers ----->')
plt.ylabel('Accuracies ---->')
plt.title('ACCURACIES RESULTED')
plt.show()
20XX presentation title 14
Output
15
Modules
 Data Loading: Data loading is the process of reading data from a source, such
as a file or
database, and loading it into a program or application for further processing or
analysis. It involves accessing the data, transforming it into a format that the
program can use, and then loading it into memory or storage for use.
➢ Data Cleaning: Data cleaning is the process of identifying and correcting or
removing errors, inconsistencies, and inaccuracies in a dataset. It involves
analyzing and validating the data, detecting and correcting errors, handling missing
or duplicated values, and transforming the data into a usable format for analysis.
Data cleaning ensures that the data is accurate, complete, and reliable for further
analysis or modeling.
➢ Data Visualisation: Data visualization is the process of creating graphical
representations of data to help people understand and interpret complex
information. It involves transforming raw data into visual formats such as charts,
graphs, and maps, that can be easily interpreted and understood. Data
visualization helps to identify patterns, relationships, and trends in the data, and
communicate them effectively to stakeholders.
➢ Data Pre Processing: Data preprocessing refers to the process of preparing
and cleaning raw data before it can be used for analysis or modeling. Here are
some common steps in data preprocessing.
20XX presentation title 16
CONCLUSION
In conclusion, this study has demonstrated the potential benefits of developing a
productivity prediction model for garment employees that can accurately forecast the
amount of clothes that need to be produced in the coming years based on input and
sales data from previous years. By utilizing machine learning algorithms such as linear
regression, decision trees, and neural networks, and data mining techniques, predictive
models can be developed that can improve the accuracy of demand forecasting and
production planning in the garment manufacturing industry. However, further research is
required to validate and optimize the proposed productivity prediction model and to
address challenges related to data quality, model interpretability, and implementation in
real-world settings. With continued research, the development of accurate productivity
prediction models can lead to improved operational efficiency, reduced costs, and
increased profitability in the garment manufacturing industry.
20XX presentation title 17
REFERENCES
 Google
 Chatgpt
 Kaggle
20XX presentation title 18
Thank You

More Related Content

Similar to Prediction of Garment based on previous usage

Documentation on bigmarket copy
Documentation on bigmarket   copyDocumentation on bigmarket   copy
Documentation on bigmarket copyswamypotharaveni
 
Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides SlideTeam
 
Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides SlideTeam
 
6 sigma assignment
6 sigma assignment6 sigma assignment
6 sigma assignmentstudent
 
Lace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printableLace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printableFabrizio Cardinali
 
Company Operations Powerpoint Presentation Slides
Company Operations Powerpoint Presentation SlidesCompany Operations Powerpoint Presentation Slides
Company Operations Powerpoint Presentation SlidesSlideTeam
 
Agile Manufacturing - Four components
Agile Manufacturing - Four componentsAgile Manufacturing - Four components
Agile Manufacturing - Four componentsWORKERBASE
 
Supply Chain Management Workshop
Supply Chain Management WorkshopSupply Chain Management Workshop
Supply Chain Management WorkshopTom Sauder, P.Eng.
 
BIG MART SALES PREDICTION USING MACHINE LEARNING
BIG MART SALES PREDICTION USING MACHINE LEARNINGBIG MART SALES PREDICTION USING MACHINE LEARNING
BIG MART SALES PREDICTION USING MACHINE LEARNINGIRJET Journal
 
Optimization of supply chain logistics cost
Optimization of supply chain logistics costOptimization of supply chain logistics cost
Optimization of supply chain logistics costIAEME Publication
 
Optimization of supply chain logistics cost
Optimization of supply chain logistics costOptimization of supply chain logistics cost
Optimization of supply chain logistics costIAEME Publication
 
QM-009-Design for Six Sigma 2
QM-009-Design for Six Sigma 2QM-009-Design for Six Sigma 2
QM-009-Design for Six Sigma 2handbook
 
Introduction to Six Sigma
Introduction to Six Sigma Introduction to Six Sigma
Introduction to Six Sigma Vijay Rasam
 

Similar to Prediction of Garment based on previous usage (20)

Six sigma
Six sigma Six sigma
Six sigma
 
Documentation on bigmarket copy
Documentation on bigmarket   copyDocumentation on bigmarket   copy
Documentation on bigmarket copy
 
Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides
 
Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides Company Operations PowerPoint Presentation Slides
Company Operations PowerPoint Presentation Slides
 
Six Sigma
Six SigmaSix Sigma
Six Sigma
 
6 sigma assignment
6 sigma assignment6 sigma assignment
6 sigma assignment
 
Six sigma training
Six sigma trainingSix sigma training
Six sigma training
 
Six sigma training
Six sigma trainingSix sigma training
Six sigma training
 
Lace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printableLace project transforming workplace learning in manufacturing printable
Lace project transforming workplace learning in manufacturing printable
 
Introduction to Six Sigma
Introduction to Six SigmaIntroduction to Six Sigma
Introduction to Six Sigma
 
Company Operations Powerpoint Presentation Slides
Company Operations Powerpoint Presentation SlidesCompany Operations Powerpoint Presentation Slides
Company Operations Powerpoint Presentation Slides
 
Agile Manufacturing - Four components
Agile Manufacturing - Four componentsAgile Manufacturing - Four components
Agile Manufacturing - Four components
 
Supply Chain Management Workshop
Supply Chain Management WorkshopSupply Chain Management Workshop
Supply Chain Management Workshop
 
BIG MART SALES PREDICTION USING MACHINE LEARNING
BIG MART SALES PREDICTION USING MACHINE LEARNINGBIG MART SALES PREDICTION USING MACHINE LEARNING
BIG MART SALES PREDICTION USING MACHINE LEARNING
 
Optimization of supply chain logistics cost
Optimization of supply chain logistics costOptimization of supply chain logistics cost
Optimization of supply chain logistics cost
 
Optimization of supply chain logistics cost
Optimization of supply chain logistics costOptimization of supply chain logistics cost
Optimization of supply chain logistics cost
 
yellow belt training
yellow belt trainingyellow belt training
yellow belt training
 
DFSS short
DFSS shortDFSS short
DFSS short
 
QM-009-Design for Six Sigma 2
QM-009-Design for Six Sigma 2QM-009-Design for Six Sigma 2
QM-009-Design for Six Sigma 2
 
Introduction to Six Sigma
Introduction to Six Sigma Introduction to Six Sigma
Introduction to Six Sigma
 

Recently uploaded

BLOOM_April2024. Balmer Lawrie Online Monthly Bulletin
BLOOM_April2024. Balmer Lawrie Online Monthly BulletinBLOOM_April2024. Balmer Lawrie Online Monthly Bulletin
BLOOM_April2024. Balmer Lawrie Online Monthly BulletinBalmerLawrie
 
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024Richard Ingilby
 
The+State+of+Careers+In+Retention+Marketing-2.pdf
The+State+of+Careers+In+Retention+Marketing-2.pdfThe+State+of+Careers+In+Retention+Marketing-2.pdf
The+State+of+Careers+In+Retention+Marketing-2.pdfSocial Samosa
 
April 2024 - VBOUT Partners Meeting Group
April 2024 - VBOUT Partners Meeting GroupApril 2024 - VBOUT Partners Meeting Group
April 2024 - VBOUT Partners Meeting GroupVbout.com
 
What is Google Search Console and What is it provide?
What is Google Search Console and What is it provide?What is Google Search Console and What is it provide?
What is Google Search Console and What is it provide?riteshhsociall
 
Social Samosa Guidebook for SAMMIES 2024.pdf
Social Samosa Guidebook for SAMMIES 2024.pdfSocial Samosa Guidebook for SAMMIES 2024.pdf
Social Samosa Guidebook for SAMMIES 2024.pdfSocial Samosa
 
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort ServiceEnjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort ServiceDelhi Call girls
 
Cost-effective tactics for navigating CPC surges
Cost-effective tactics for navigating CPC surgesCost-effective tactics for navigating CPC surges
Cost-effective tactics for navigating CPC surgesPushON Ltd
 
Social Media Marketing PPT-Includes Paid media
Social Media Marketing PPT-Includes Paid mediaSocial Media Marketing PPT-Includes Paid media
Social Media Marketing PPT-Includes Paid mediaadityabelde2
 
Google 3rd-Party Cookie Deprecation [Update] + 5 Best Strategies
Google 3rd-Party Cookie Deprecation [Update] + 5 Best StrategiesGoogle 3rd-Party Cookie Deprecation [Update] + 5 Best Strategies
Google 3rd-Party Cookie Deprecation [Update] + 5 Best StrategiesSearch Engine Journal
 
Local SEO Domination: Put your business at the forefront of local searches!
Local SEO Domination:  Put your business at the forefront of local searches!Local SEO Domination:  Put your business at the forefront of local searches!
Local SEO Domination: Put your business at the forefront of local searches!dstvtechnician
 
Uncover Insightful User Journey Secrets Using GA4 Reports
Uncover Insightful User Journey Secrets Using GA4 ReportsUncover Insightful User Journey Secrets Using GA4 Reports
Uncover Insightful User Journey Secrets Using GA4 ReportsVWO
 
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...ChesterYang6
 
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15SearchNorwich
 
Unraveling the Mystery of the Hinterkaifeck Murders.pptx
Unraveling the Mystery of the Hinterkaifeck Murders.pptxUnraveling the Mystery of the Hinterkaifeck Murders.pptx
Unraveling the Mystery of the Hinterkaifeck Murders.pptxelizabethella096
 
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort ServiceDelhi Call girls
 

Recently uploaded (20)

BLOOM_April2024. Balmer Lawrie Online Monthly Bulletin
BLOOM_April2024. Balmer Lawrie Online Monthly BulletinBLOOM_April2024. Balmer Lawrie Online Monthly Bulletin
BLOOM_April2024. Balmer Lawrie Online Monthly Bulletin
 
BUY GMAIL ACCOUNTS PVA USA IP INDIAN IP GMAIL
BUY GMAIL ACCOUNTS PVA USA IP INDIAN IP GMAILBUY GMAIL ACCOUNTS PVA USA IP INDIAN IP GMAIL
BUY GMAIL ACCOUNTS PVA USA IP INDIAN IP GMAIL
 
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
 
The+State+of+Careers+In+Retention+Marketing-2.pdf
The+State+of+Careers+In+Retention+Marketing-2.pdfThe+State+of+Careers+In+Retention+Marketing-2.pdf
The+State+of+Careers+In+Retention+Marketing-2.pdf
 
April 2024 - VBOUT Partners Meeting Group
April 2024 - VBOUT Partners Meeting GroupApril 2024 - VBOUT Partners Meeting Group
April 2024 - VBOUT Partners Meeting Group
 
What is Google Search Console and What is it provide?
What is Google Search Console and What is it provide?What is Google Search Console and What is it provide?
What is Google Search Console and What is it provide?
 
Social Samosa Guidebook for SAMMIES 2024.pdf
Social Samosa Guidebook for SAMMIES 2024.pdfSocial Samosa Guidebook for SAMMIES 2024.pdf
Social Samosa Guidebook for SAMMIES 2024.pdf
 
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort ServiceEnjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Dlf City Phase 4 Gurgaon >༒8448380779 Escort Service
 
Cost-effective tactics for navigating CPC surges
Cost-effective tactics for navigating CPC surgesCost-effective tactics for navigating CPC surges
Cost-effective tactics for navigating CPC surges
 
Social Media Marketing PPT-Includes Paid media
Social Media Marketing PPT-Includes Paid mediaSocial Media Marketing PPT-Includes Paid media
Social Media Marketing PPT-Includes Paid media
 
Google 3rd-Party Cookie Deprecation [Update] + 5 Best Strategies
Google 3rd-Party Cookie Deprecation [Update] + 5 Best StrategiesGoogle 3rd-Party Cookie Deprecation [Update] + 5 Best Strategies
Google 3rd-Party Cookie Deprecation [Update] + 5 Best Strategies
 
Local SEO Domination: Put your business at the forefront of local searches!
Local SEO Domination:  Put your business at the forefront of local searches!Local SEO Domination:  Put your business at the forefront of local searches!
Local SEO Domination: Put your business at the forefront of local searches!
 
Uncover Insightful User Journey Secrets Using GA4 Reports
Uncover Insightful User Journey Secrets Using GA4 ReportsUncover Insightful User Journey Secrets Using GA4 Reports
Uncover Insightful User Journey Secrets Using GA4 Reports
 
Generative AI Master Class - Generative AI, Unleash Creative Opportunity - Pe...
Generative AI Master Class - Generative AI, Unleash Creative Opportunity - Pe...Generative AI Master Class - Generative AI, Unleash Creative Opportunity - Pe...
Generative AI Master Class - Generative AI, Unleash Creative Opportunity - Pe...
 
No Cookies No Problem - Steve Krull, Be Found Online
No Cookies No Problem - Steve Krull, Be Found OnlineNo Cookies No Problem - Steve Krull, Be Found Online
No Cookies No Problem - Steve Krull, Be Found Online
 
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...
Netflix Ads The Game Changer in Video Ads – Who Needs YouTube.pptx (Chester Y...
 
Top 5 Breakthrough AI Innovations Elevating Content Creation and Personalizat...
Top 5 Breakthrough AI Innovations Elevating Content Creation and Personalizat...Top 5 Breakthrough AI Innovations Elevating Content Creation and Personalizat...
Top 5 Breakthrough AI Innovations Elevating Content Creation and Personalizat...
 
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15
Five Essential Tools for International SEO - Natalia Witczyk - SearchNorwich 15
 
Unraveling the Mystery of the Hinterkaifeck Murders.pptx
Unraveling the Mystery of the Hinterkaifeck Murders.pptxUnraveling the Mystery of the Hinterkaifeck Murders.pptx
Unraveling the Mystery of the Hinterkaifeck Murders.pptx
 
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 128 Noida Escorts >༒8448380779 Escort Service
 

Prediction of Garment based on previous usage

  • 1. TITLE PRODUCTIVITY PREDICTION OF GARMENT EMPLOYEES Under the guidance of: Mrs.G.Vijaya Laxmi(Associative Professor) Miss.J.Madhavi(Assistant Professor) Department of Computer Science and Engineering in Artificial Intelligence and Machine Learning (CSE – AI & ML)
  • 3. Introduction  The Garment Industry is one of the key examples of the industrial globalization of this modern era. It is a highly labor-intensive industry with lots of manual processes.  Satisfying the huge global demand for garment products is mostly dependent on the production and delivery performance of the employees in the garment manufacturing companies.  So, it is highly desirable among the decision-makers in the garments industry to track, analyze, and predict the productivity performance of the working teams in their factories. 3
  • 4. Abstract  The garment industry is one of the key examples of the industrial globalization of this modern era. It is a highly labor- intensive industry with lots of manual processes. Satisfying the huge global demand for garment products is mostly dependent on the production and delivery performance of the employees in the garment manufacturing companies.  So, it is highly desirable among the garment industry decision- makers to track, analyze, and predict the productivity performance of the working teams in their factories. This study explores the application of state-of-the-art data mining techniques for analyzing industrial data, revealing meaningful insights, and predicting the productivity performance of the working teams in a garment company.  We have applied eight different data mining techniques with six evaluation metrics as part of our exploration. 4
  • 5. Existing Systems  Raw-Material Issue. Raw materials are essential to the garment industry  Inventory Management Issue  Production Delays  Order Processing Issue  Garment Defects 5
  • 6. Proposed Systems  If you are working in garment production or planning to open your own garment company, you would need an all-in-one solution that can help you to solve these challenges and issues and improve your business productivity and performance. Garments ERP management software is designed to help you overcome these operational challenges. From planning, manufacturing, and order processing to distribution, this robust software can easily handle all your operational tasks and distribution activities.  All manufacturing industries deal with various challenges and issues in their product manufacturing processes. That is why today we will discuss five common problems that all garment manufacturers face that hamper their product quality and production performance. 6
  • 7. MERITS AND DEMERITS MERITS It is used to reduce work pressure of an employee. It helps in saving raw materials. It is used as a guide for those who are starting new garment industries. By using this we can save money. It will help an industries to gain profits. DEMERITS Retraining is not possible in Machine Learning. The data we give for training should me accurate otherwise the result will be incorrect. 20XX presentation title 7
  • 8. ALGORITHMS USED K-Nearest Neighbors algorithm Linear Regression Support Vector Machine Decision Tree Using Regression Random Forest 20XX presentation title 8
  • 10. Requirements Hardware Requirements  RAM(8GB)  ROM(64 bitprocessor)  Windows 10  HARD DISK 256GB  I5 PROCESSOR Software Requirements  Python  Python 3  Libraries  NumPy  OpenCV, etc 10
  • 11. Code import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import numpy as np import sklearn df = pd.read_csv('/content/drive/MyDrive/garments_worker_productivity.csv') df.head() df.shape df.describe() df2 = df.drop(['date', 'day'], axis=1) df2.shape df3 = df2.fillna({'wip': 0,}) df3.isnull().sum() plt.figure(figsize=(10,5)) p = sns.boxplot(data = df3, orient ='v',width=0.8) plt.xticks(rotation=90) Q1 = df3.incentive.quantile(0.25) Q3 = df3.incentive.quantile(0.75) Q1, Q3 11
  • 12. IQR = Q3 - Q1 IQR lower_limit = Q1 - 1.5*IQR upper_limit = Q3 + 1.5*IQR lower_limit, upper_limit df3[(df3.incentive<lower_limit)|(df3.incentive>upper_limit)] df4 = df3[(df3.incentive>lower_limit)&(df3.incentive<upper_limit)] df4.shape Q1 = df4.wip.quantile(0.25) Q3 = df4.wip.quantile(0.75) Q1, Q3 IQR = Q3 - Q1 IQR lower_limit = Q1 - 1.5*IQR upper_limit = Q3 + 1.5*IQR lower_limit, upper_limit df4[(df4.wip<lower_limit)|(df4.wip>upper_limit)] df5 = df4[(df4.wip>lower_limit)&(df4.wip<upper_limit)] df5.shape Q1 = df5.over_time.quantile(0.25) Q3 = df5.over_time.quantile(0.75) Q1, Q3 IQR = Q3 - Q1 IQR lower_limit = Q1 - 1.5*IQR 12
  • 13. upper_limit = Q3 + 1.5*IQR lower_limit, upper_limit df5[(df5.over_time<lower_limit)|(df5.over_time>upper_limit)] df6 = df5[(df5.over_time>lower_limit)&(df5.over_time<upper_limit)] df6.shape lt.figure(figsize=(10,5)) p = sns.boxplot(data = df6, orient ='v',width=0.8) plt.xticks(rotation=90) from sklearn.preprocessing import LabelEncoder le = LabelEncoder() for i in range(0, df6.shape[1]): if df6.dtypes[i]=='object': df6[df6.columns[i]] = le.fit_transform(df6[df6.columns[i]]) x = df6.drop(['actual_productivity'], axis=1) y = df6.actual_productivity x.shape, y.shape y.head() from sklearn.preprocessing import StandardScaler scaler = StandardScaler() x.iloc[:,:] = scaler.fit_transform(x.iloc[:,:]) x.head() sns.pairplot(df,hue = "team") plt.figure(figsize=(12, 10)) sns.heatmap(df6.corr(), annot=True,vmin=-1,vmax=1,cmap='viridis',square=True) 13
  • 14. df.iloc[:, 1:].plot.density(subplots=True, layout=(1,11), figsize=(20, 10), sharex = False) df_wip = df[df.wip > 0] sns.barplot(x="day", y="wip", data=df_wip) df_diff = df["actual_productivity"] - df["targeted_productivity"] sns.lineplot(x = df["date"], y = df_diff, ci = None) from sklearn.model_selection import train_test_split x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.30, random_state=42) print(x_train.shape) print(x_test.shape) print(y_train.shape) print(y_test.shape) import matplotlib.pyplot as plt fig = plt.figure() ax = fig.add_axes([0,0,1,1]) algo = ['Linear regression','knr','SVr','Descision Tree','Random Forest'] accuracy = [linreg.score(x,y),knn.score(x,y),svr.score(x,y),dt.score(x,y),randf.score(x,y)] ax.bar(algo[0],accuracy[0],color = 'g') ax.bar(algo[1],accuracy[1],color = 'b') ax.bar(algo[2],accuracy[2],color = 'y') ax.bar(algo[3],accuracy[3],color = 'r') ax.bar(algo[4],accuracy[4],color = 'y') plt.xlabel('Classifiers ----->') plt.ylabel('Accuracies ---->') plt.title('ACCURACIES RESULTED') plt.show() 20XX presentation title 14
  • 16. Modules  Data Loading: Data loading is the process of reading data from a source, such as a file or database, and loading it into a program or application for further processing or analysis. It involves accessing the data, transforming it into a format that the program can use, and then loading it into memory or storage for use. ➢ Data Cleaning: Data cleaning is the process of identifying and correcting or removing errors, inconsistencies, and inaccuracies in a dataset. It involves analyzing and validating the data, detecting and correcting errors, handling missing or duplicated values, and transforming the data into a usable format for analysis. Data cleaning ensures that the data is accurate, complete, and reliable for further analysis or modeling. ➢ Data Visualisation: Data visualization is the process of creating graphical representations of data to help people understand and interpret complex information. It involves transforming raw data into visual formats such as charts, graphs, and maps, that can be easily interpreted and understood. Data visualization helps to identify patterns, relationships, and trends in the data, and communicate them effectively to stakeholders. ➢ Data Pre Processing: Data preprocessing refers to the process of preparing and cleaning raw data before it can be used for analysis or modeling. Here are some common steps in data preprocessing. 20XX presentation title 16
  • 17. CONCLUSION In conclusion, this study has demonstrated the potential benefits of developing a productivity prediction model for garment employees that can accurately forecast the amount of clothes that need to be produced in the coming years based on input and sales data from previous years. By utilizing machine learning algorithms such as linear regression, decision trees, and neural networks, and data mining techniques, predictive models can be developed that can improve the accuracy of demand forecasting and production planning in the garment manufacturing industry. However, further research is required to validate and optimize the proposed productivity prediction model and to address challenges related to data quality, model interpretability, and implementation in real-world settings. With continued research, the development of accurate productivity prediction models can lead to improved operational efficiency, reduced costs, and increased profitability in the garment manufacturing industry. 20XX presentation title 17
  • 18. REFERENCES  Google  Chatgpt  Kaggle 20XX presentation title 18