Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Machine Learning Basics for a Newbie
6 Steps of Machine learning Lifecycle Introduction to Predictive Modeling
Introduction to Exploratory Data Analysis & Data Insights Descriptive Statistics Inferential Statistics How to Understand Population Distributions?
Reading Data Files into Python Different Variable Datatypes
Probability for Data Science Basic Concepts of Probability Axioms of Probability Conditional Probability
Central Tendencies for Continuous Variables Spread of Data KDE plots for Continuous Variable Overview of Distribution for Continuous variables Normal Distribution Skewed Distribution Skeweness and Kurtosis Distribution for Continuous Variable
Central Tendencies for Categorical Variables Understanding Discrete Distributions Performing EDA on Categorical Variables
Dealing with Missing Values Understanding Outliers Identifying Outliers in Data Outlier Detection in Python Outliers Detection Using IQR, Z-score, LOF and DBSCAN
Sample and Population Central Limit Theorem Confidence Interval and Margin of Error
Bivariate Analysis Introduction
Covariance Pearson Correlation Spearman's Correlation & Kendall's Tau Correlation versus Causation Tabular and Graphical methods for Bivariate Analysis Performing Bivariate Analysis on Continuous-Continuous Variables
Tabular and Graphical methods for Continuous-Categorical Variables Introduction to Hypothesis Testing P-value Two sample Z-test T-test T-test vs Z-test Performing Bivariate Analysis on Continuous-Catagorical variables
Chi-Squares Test Bivariate Analysis on Categorical Categorical Variables
Multivariate Analysis A Comprehensive Guide to Data Exploration The Data Science behind IPL
Supervised Learning vs Unsupervised Learning Reinforcement Learning Generative and Descriminative Models Parametric and Non Parametric model
Machine Learning Pipeline Preparing Dataset Build a Benchmark Model: Regression Build a Benchmark Model: Classification
Evaluation Metrics for Machine Learning Everyone should know Confusion Matrix Accuracy Precision and Recall AUC-ROC Log Loss R2 and Adjusted R2
Dealing with Missing Values Replacing Missing Values Imputing Missing Values in Data Working with Categorical Variables Working with Outliers Preprocessing Data for Model Building
Understanding Cost Function Understanding Gradient Descent Math Behind Gradient Descent Assumptions of Linear Regression Implement Linear Regression from Scratch Train Linear Regression in Python Implementing Linear Regression in R Diagnosing Residual Plots in Linear Regression Models Generalized Linear Models Introduction to Logistic Regression Odds Ratio Implementing Logistic Regression from Scratch Introduction to Scikit-learn in Python Train Logistic Regression in python Multiclass using Logistic Regression How to use Multinomial and Ordinal Logistic Regression in R ? Challenges with Linear Regression Introduction to Regularisation Implementing Regularisation Ridge Regression Lasso Regression
Introduction to K Nearest Neighbours Determining the Right Value of K in KNN Implement KNN from Scratch Implement KNN in Python
Bias Variance Tradeoff Introduction to Overfitting and Underfitting Visualizing Overfitting and Underfitting Selecting the Right Model What is Validation? Hold-Out Validation Understanding K Fold Cross Validation
Introduction to Feature Selection Feature Selection Algorithms Missing Value Ratio Low Variance Filter High Correlation Filter Backward Feature Elimination Forward Feature Selection Implement Feature Selection in Python Implement Feature Selection in R
Introduction to Decision Tree Purity in Decision Tree Terminologies Related to Decision Tree How to Select Best Split Point in Decision Tree? Chi-Squares Information Gain Reduction in Variance Optimizing Performance of Decision Tree Train Decision Tree using Scikit Learn Pruning of Decision Trees
Introduction to Feature Engineering Feature Transformation Feature Scaling Feature Engineering Frequency Encoding Automated Feature Engineering: Feature Tools
Introduction to Naive Bayes Conditional Probability and Bayes Theorem Introduction to Bayesian Adjustment Rating: The Incredible Concept Behind Online Ratings! Working of Naive Bayes Math behind Naive Bayes Types of Naive Bayes Implementation of Naive Bayes
Understanding how to solve Multiclass and Multilabled Classification Problem Evaluation Metrics: Multi Class Classification
Introduction to Ensemble Techniques Basic Ensemble Techniques Implementing Basic Ensemble Techniques Finding Optimal Weights of Ensemble Learner using Neural Network Why Ensemble Models Work well?
Introduction to Stacking Implementing Stacking Variants of Stacking Implementing Variants of Stacking Introduction to Blending Bootstrap Sampling Introduction to Random Sampling Hyper-parameters of Random Forest Implementing Random Forest Out-of-Bag (OOB) Score in the Random Forest IPL Team Win Prediction Project Using Machine Learning Introduction to Boosting Gradient Boosting Algorithm Math behind GBM Implementing GBM in python Regularized Greedy Forests Extreme Gradient Boosting Implementing XGBM in python Tuning Hyperparameters of XGBoost in Python Implement XGBM in R/H2O Adaptive Boosting Implementing Adaptive Boosing LightGBM Implementing LightGBM in Python Catboost Implementing Catboost in Python
Different Hyperparameter Tuning methods Implementing Different Hyperparameter Tuning methods GridsearchCV RandomizedsearchCV Bayesian Optimization for Hyperparameter Tuning Hyperopt
Understanding SVM Algorithm SVM Kernels In-depth Intuition and Practical Implementation SVM Kernel Tricks Kernels and Hyperparameters in SVM Implementing SVM from Scratch in Python and R
Introduction to Principal Component Analysis Steps to Perform Principal Compound Analysis Computation of Covariance Matrix Finding Eigenvectors and Eigenvalues Implementing PCA in python Visualizing PCA A Brief Introduction to Linear Discriminant Analysis Introduction to Factor Analysis
Introduction to Clustering Applications of Clustering Evaluation Metrics for Clustering Understanding K-Means Implementation of K-Means in Python Implementation of K-Means in R Choosing Right Value for K Profiling Market Segments using K-Means Clustering Hierarchical Clustering Implementation of Hierarchial Clustering DBSCAN Defining Similarity between clusters Build Better and Accurate Clusters with Gaussian Mixture Models
Understand Basics of Recommendation Engine with Case Study
8 Ways to Improve Accuracy of Machine Learning Models
Introduction to Dask Working with CuML
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to AutoML Implementation of MLBox Introduction to PyCaret TPOT Auto-Sklearn EvalML
Pickle and Joblib Introduction to Model Deployment
Deploying Machine Learning Model using Streamlit Deploying ML Models in Docker Deploy Using Streamlit Deploy on Heroku Deploy Using Netlify Introduction to Amazon Sagemaker Setting up Amazon SageMaker Using SageMaker Endpoint to Generate Inference Deploy on Microsoft Azure Cloud Introduction to Flask for Model Deploying ML model using Flask
Model Deployment in Android Model Deployment in Iphone

How I Won My First Public Data Science Competition?

A
Alifia Ghantiwala Last Updated : 22 Mar, 2022
8 min read

This article was published as a part of the Data Science Blogathon.

Data Science Competition
Source: Author

About the Competition

The competition was to predict the likelihood of having Autism. It was sponsored by Google Developers and hosted on Kaggle. The data was collected from people that filled out an app form. Research has proven that early detection of autism can help in incrementing mental development, communication, and social skills. This was the main driving force of the challenge, to provide an automated and reliable solution to healthcare workers so that they can prioritize their resources.

The Approach I Followed to Win the Competition

0) Understanding the data
1) Using label encoder to encode categorical features
2) Removal of features based on their correlation with the target
3) Using Grid Search and 5 fold cross-validation for hyperparameter optimization.
4) For modelling, I used XGBoost and LightGBM and combined their results based on CV performance.

Understanding the Data

Understanding the data would be our first step. The most powerful machine learning model would not produce desired results with garbage input. I did a univariate and bivariate analysis to understand the input completely, based on the same, I did feature selection.

Features in our dataset

ID – ID of the patient
A1_Score to A10_Score – Score based on Autism Spectrum Quotient (AQ)
age – Patient’s age in years
gender – Gender of the patient
ethnicity – Ethnicity of the patient
jaundice – Whether the person was having jaundice at birth
autism – If an immediate family member was diagnosed with autism
contry_of_res – Country of patient
used_app_before – If a person has undergone a screening test
result – Score for AQ1-10 screening test
age_desc – Age of the patient
relation – Relation of a patient who completed the test
Class/ASD – Target label
train.columns
Data Science Competition

Source: Author

 



Univariate Analysis


ncounts = pd.<a onclick="parent.postMessage({'referent':'.pandas.DataFrame'}, '*')">DataFrame([train.isna().mean(), test.isna().mean()]).T
ncounts = ncounts.rename(columns={0: "train_missing", 1: "test_missing"})

ncounts.query("train_missing > 0")




Univariate Analysis | Data Science Competition




Source: Author


The input data does not have NA values.


Gender feature


sns.<a onclick="parent.postMessage({'referent':'.seaborn.set_theme'}, '*')">set_theme(style="darkgrid")
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='gender',data=train)




Gender Feature | Data Science Competition
Source: Author




Ethnicity


plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15,15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='ethnicity',data=train)




Ethnicity | Data Science Competition
Source: Author




Relation feature


sns.<a onclick="parent.postMessage({'referent':'.seaborn.set_theme'}, '*')">set_theme(style="darkgrid")
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15,15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='relation',data=train)




Relation Feature | Data Science Competition
Source: Author




Age feature


sns.<a onclick="parent.postMessage({'referent':'.seaborn.set_theme'}, '*')">set_theme(style="darkgrid")
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15,15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='age_desc',data=train)




Age Feature | Data Science Competition
Source: Author




We have 800 different age values but all of them are older than 800




Jaundice feature


sns.<a onclick="parent.postMessage({'referent':'.seaborn.set_theme'}, '*')">set_theme(style="darkgrid")
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15,15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='jaundice',data=train)




Source: Author




 


Autism feature


sns.<a onclick="parent.postMessage({'referent':'.seaborn.set_theme'}, '*')">set_theme(style="darkgrid")
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15,15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(x='austim',data=train)




Source: Author




Country of patient feature


train["contry_of_res"].value_counts()




Source: Author




A1 to A10 score feature


score_columns = ["A1_Score","A2_Score","A3_Score","A4_Score","A5_Score","A6_Score","A7_Score","A8_Score","A9_Score","A10_Score"]
i = 1
for col in score_columns:
    plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(10,15))
    plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.subplot'}, '*')">subplot(10,1,i)
    sns.<a onclick="parent.postMessage({'referent':'.seaborn.countplot'}, '*')">countplot(train[col])
    i += 1




















 


Result (target feature)


train["result"].describe()




Source: Author




sns.<a onclick="parent.postMessage({'referent':'.seaborn.scatterplot'}, '*')">scatterplot(data=train,x="result",y="Class/ASD")




Source: Author




Observation: Result values less than 0 are only class 0 target




Insights from Univariate Analysis




    

  • 

    No missing/NA data
    

    • 

  • No columns with constant values
    • 

  • Gender distribution in the train and test datasets is the same and is balanced.
    • 

  • The highest number of patients are from ethnicity ‘White European’ in both test and train data. We have a lot of values with ethnicity ?, what could be a suitable replacement strategy?
    • 

  • Most people are completing the test by themselves, but we do have entries with value ?, what would be the best value to replace them logically.
    • 

  • Age variable has all unique values but we know that all of them have an age of more than 18
    • 

  • Train data contains 75% of people that did not have jaundice when they were born. Test data has a similar distribution
    • 

  • The country feature has 61 unique values in the training dataset and the United States, United Arab Emirates, New Zealand, India, and United Kingdom have the highest record counts in that order in the training dataset. In the test dataset, we have 44 unique values of countries United States, United Arab Emirates, New Zealand, Jordan, and India are the top contributors in that order.
    • 

  • Majority of the data that we have did not have a family member having autism.
    • 

  • A1_score to A10_score are binary features that are encoded, we would look at its correlation with the target class variable to understand it better.
    • 

  • Result values in the train data have a min of -2 and a maximum of 13 with a mean of 7
    • 

  • A scatterplot between result and class, tell us that result values less than 0 have a class of negative in the train data
    • 







Bivariate Analysis


To understand the correlation of A1 to A10 feature scores with the class variable we plot the below heatmap.


correlation_columns = []
for col in score_columns:
    correlation_columns.append(col)
correlation_columns.append("Class/ASD")


correlation = train[correlation_columns].corr()
mask = np.<a onclick="parent.postMessage({'referent':'.numpy.triu'}, '*')">triu(np.<a onclick="parent.postMessage({'referent':'.numpy.ones_like'}, '*')">ones_like(correlation, dtype=np.<a onclick="parent.postMessage({'referent':'.numpy.bool'}, '*')">bool))
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(11, 9))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(correlation,annot=True,mask=mask)








Source: Author


A3, A6, A9, A4, A5, and A10 have a correlation higher than 0.4


Let’s find out how age correlates with the target


correlation = train[["age","result","Class/ASD"]].corr()
mask = np.<a onclick="parent.postMessage({'referent':'.numpy.triu'}, '*')">triu(np.<a onclick="parent.postMessage({'referent':'.numpy.ones_like'}, '*')">ones_like(correlation, dtype=np.<a onclick="parent.postMessage({'referent':'.numpy.bool'}, '*')">bool))
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(11, 9))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(correlation,annot=True,mask=mask)




Source: Author




Age does not seem to have a very high correlation value with the target


For understanding the relationship between gender and target we plot the below.


sns.<a onclick="parent.postMessage({'referent':'.seaborn.boxplot'}, '*')">boxplot(data=train,x='gender',y='Class/ASD')




Source: Author




from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
transformed_gender = le.fit_transform(train["gender"])
train["transformed_gender"] = transformed_gender
corre = train[["transformed_gender","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)




Source: Author




The correlation between gender and target seems to be weak.


Can the country where the patient resides have an effect? Let’s find out.


plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(20, 15))
top_5  = ["United States", "United Arab Emirates", "New Zealand", "India" , "United Kingdom"]
train_subset = train.loc[train["contry_of_res"].isin(top_5)]
sns.<a onclick="parent.postMessage({'referent':'.seaborn.boxplot'}, '*')">boxplot(data=train_subset,x='contry_of_res',y='Class/ASD')




Source: Author




le = LabelEncoder()
transformed_country = le.fit_transform(train["contry_of_res"])
train["transformed_country"] = transformed_country
corre = train[["transformed_country","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)




Source: Author




Let us now see if ethnicity correlates with our target


chart = sns.<a onclick="parent.postMessage({'referent':'.seaborn.boxplot'}, '*')">boxplot(data=train,x='ethnicity',y='Class/ASD')
chart.set_xticklabels(chart.get_xticklabels(), rotation=45)




Source: Author




It seems we have two values others and Others in the ethnicity feature which have the same meaning. Let’s clean it out


train['ethnicity'] = train['ethnicity'].replace('others','Others')


le = LabelEncoder()
transformed_ethnicity = le.fit_transform(train["ethnicity"])
train["transformed_ethnicity"] = transformed_ethnicity
corre = train[["transformed_ethnicity","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)




Data Science Competition
Source: Author




Ethnicity seems to have a decent correlation with the target


Understanding the relationship between jaundice and the target


chart = sns.<a onclick="parent.postMessage({'referent':'.seaborn.boxplot'}, '*')">boxplot(data=train,x='jaundice',y='Class/ASD')




Jaundice and Target | Data Science Competition
Source: Author




le = LabelEncoder()
transformed_jaundice = le.fit_transform(train["jaundice"])
train["transformed_jaundice"] = transformed_jaundice
corre = train[["transformed_jaundice","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)








Jaundice seems to have a decent correlation with the target


Correlation of autism feature with the target variable


le = LabelEncoder()
transformed_austim = le.fit_transform(train["austim"])
train["transformed_austim"] = transformed_austim
corre = train[["transformed_austim","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)
transformed_austim_te = le.fit_transform(test["austim"])
test["transformed_austim"] = transformed_austim_te




Data Science Competition
Source: Author


Autism seems to have a decent correlation with the target






le = LabelEncoder()
transformed_used_app_before = le.fit_transform(train["used_app_before"])
train["transformed_used_app_before"] = transformed_used_app_before
corre = train[["transformed_used_app_before","Class/ASD"]].corr()
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(corre,annot=True)




Data Science Competition
Source: Author




used_app_before does not have a high correlation with the target


correlation = train.corr()
mask = np.<a onclick="parent.postMessage({'referent':'.numpy.triu'}, '*')">triu(np.<a onclick="parent.postMessage({'referent':'.numpy.ones_like'}, '*')">ones_like(correlation, dtype=np.<a onclick="parent.postMessage({'referent':'.numpy.bool'}, '*')">bool))
plt.<a onclick="parent.postMessage({'referent':'.matplotlib.pyplot.figure'}, '*')">figure(figsize=(15, 15))
sns.<a onclick="parent.postMessage({'referent':'.seaborn.heatmap'}, '*')">heatmap(correlation,annot=True,mask=mask)




Heatmap | Data Science Competition
Source: Author




Features with the Highest Correlation to the Target 


A3_Score


A2_Score


A4_Score


A5_Score


A6_Score


A7_Score


A9_Score


A10_Score


Autism


Ethnicity


Result


We would keep only these features in our data frame which would be used as input for our model.


train = train[["A3_Score","A2_Score","A4_Score","A5_Score","A6_Score","A7_Score","A9_Score","A10_Score","transformed_austim","Class/ASD","result"]]
test = test[["A3_Score","A2_Score","A4_Score","A5_Score","A6_Score","A7_Score","A9_Score","A10_Score","transformed_austim","result"]]
y = train["Class/ASD"]
train = train.drop(["Class/ASD"],axis=1)


Importing all required libraries


from sklearn.model_selection import train_test_split, StratifiedKFold, GridSearchCV
from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
from sklearn.impute import SimpleImputer
from sklearn.pipeline import make_pipeline
from sklearn.compose import make_column_transformer
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, accuracy_score
from sklearn.ensemble import RandomForestClassifier

# Models
from xgboost import XGBClassifier, XGBRegressor
from catboost import CatBoostClassifier
from lightgbm import LGBMClassifier


from sklearn.linear_model import LogisticRegression


Baseline Model


I used logistic regression as my baseline model for this problem. I have used grid search CV and Stratified K Fold with 5 folds for hyper-parameter optimization.


# Define model
model=LogisticRegression(random_state=0,class_weight='balanced')

# Parameters grid
grid_model = LogisticRegression(solver='saga',
                              C=0.22,
                              penalty='l2',class_weight='balanced')

# Cross validation
kf = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)

# Grid Search
#grid_model = GridSearchCV(model,param_grid,cv=kf)

# Train classifier with optimal parameters
grid_model.fit(train,y)


predictions = grid_model.predict(test)
pred_df = pd.<a onclick="parent.postMessage({'referent':'.pandas.DataFrame'}, '*')">DataFrame()
pred_df["ID"] = test_df["ID"]
pred_df["Class/ASD"] = predictions


pred_df[['ID', 'Class/ASD']].to_csv('submission.csv', index=False)






LightGBM


This gave me the highest performance on the public leaderboard with an AUC score of 0.931 and a private leaderboard score of 0.987




Conclusion


This could be a comprehensive starter for anyone who wants to try their hand out with Kaggle competitions.


What you must keep in mind before solving a data science problem.


1) Study the data religiously, understanding your data thoroughly will only help you to win a competition or for that matter get good results.


2) Start with a baseline model result.


3) Use bagging and boosting aggregation techniques if your problem involves classifying. If you have understood your data well, it would not be too difficult for you to select the correct model.


About the Author


I am an Analyst and like to interrogate data and share my findings through technical articles. You can read other articles published by me on Analytics Vidhya here. You can reach out to me here.


The media shown in this article is not owned by Analytics Vidhya and are used at the Author’s discretion. 

                                                

                            

                                

                                    
                                      
                                  A
                                  
                                
                                

                                

                                    
                                    Alifia Ghantiwala                                  
                                                            

                            

                            
I investigate data on a daily basis to find insights! I write so that I can understand more clearly. Have completed my graduation in Computer Engineering, and won my first public data science competition last month, March 2021, hosted on Kaggle by Google Developers.

                        

                        
                         
                    

                                       
                                        

                        
Free Courses

                        

                            
                                

                                    

                                        Generative AI
                                        
                                            
                                                
                                                
                                            4.7
                                        
                                    

                                    

                                        
Generative AI - A Way of Life

                                        
Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.

                                    

                                

                            
                        

                        

                            
                                

                                    

                                        Large Language Models
                                        
                                            
                                                
                                                
                                            4.5
                                        
                                    

                                    

                                        
Getting Started with Large Language Models

                                        
Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.

                                    

                                

                            
                        

                        

                            
                                

                                    

                                        Prompt Engineering
                                        
                                            
                                                
                                                
                                            4.6
                                        
                                    

                                    

                                        
Building LLM Applications using Prompt Engineering 

                                        
This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.

                                    

                                

                            
                        

                        

                            
                                

                                    

                                        LlamaIndex
                                        
                                            
                                                
                                                
                                            4.8
                                        
                                    

                                    

                                        
Improving Real World RAG Systems: Key Challenges & Practical Solutions

                                        
Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.

                                    

                                

                            
                        

                        

                            
                                

                                    

                                        RAG systems using LlamaIndex
                                        
                                            
                                                
                                                
                                            4.7
                                        
                                    

                                    

                                        
Microsoft Excel: Formulas & Functions

                                        
Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

                                    

                                

                            
                        

                    

                

                  
                  

                    
                    
                    

                        

                              
Recommended Articles

    

                        

                    

                

            

        

    

    
    
        
    
   
    
    


        

            

                 

                    
Responses From Readers

                    

    	

		 



Clear 


	

	                        

        








       
    
        
    
    

        

        

          

            

              
                

                  Write for us
                  
                    
                    
                  
                

                
Write, captivate, and earn accolades and rewards for your work

              
              
                
    
                  
  • Reach a Global Audience
    • 
                  
  • Get Expert Feedback
    • 
                  
  • Build Your Brand & Audience
    • 
                

                
    
                  
  • Cash In on Your Knowledge
    • 
                  
  • Join a Thriving Community
    • 
                  
  • Level Up Your Data Science Game
    • 
                

              
            

            

              
                imag
              
            

          

          
          

            

                

                    
                            

            

          

        

      

    


  
    
        

            

            

            

                

                    We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our  Privacy Policy & Cookies Policy.
                

                
Show details