"DATA SCIENCE STUDY AREAS"

WHAT it is :

Data science is the study and practice of extracting useful insights and knowledge from data. It involves collecting, processing, analyzing, and interpreting data to uncover patterns, trends, and valuable information that can be used to make informed decisions and solve problems. Data science combines various techniques from fields like statistics, mathematics, computer science, and domain expertise to derive actionable insights from large and complex datasets. Essentially, it's about turning raw data into meaningful and actionable insights.

How to work with it:✅

Working in data science involves several key steps and approaches:

Understand the Problem: Clearly define the problem or objective you want to solve using data. Understanding the business context and the specific questions you want to answer is crucial.

Data Collection and Cleaning: Gather relevant data from various sources. Clean and preprocess the data to remove inconsistencies, handle missing values, and format it properly for analysis.

Exploratory Data Analysis (EDA): Explore the data using descriptive statistics, visualizations, and summary techniques to understand its characteristics, identify patterns, and gain initial insights.

Feature Engineering and Selection: Transform and create new features from the data that are relevant for modeling. Choose the most impactful features for analysis.

Model Building: Select appropriate machine learning or statistical models based on the problem and data characteristics. Train these models using the prepared dataset.

Model Evaluation: Assess the performance of the trained models using evaluation metrics and validation techniques to ensure accuracy and reliability.

Model Deployment: Integrate the successful models into applications, systems, or processes for real-world use. Monitor and maintain the models for continued effectiveness.

Interpretation and Communication: Interpret the results and insights generated by the models. Create visualizations, reports, or presentations to effectively communicate findings to stakeholders.

Terminologies (Basic terminologies used in data science ):✅

Certainly! Here are some fundamental terminologies commonly used in data science:

### Data Related Terminologies:

1. **Dataset:** A collection of data used for analysis or experimentation.

2. **Feature:** An individual measurable property or characteristic of a dataset.

3. **Variable:** A feature or attribute that can change or take different values.

4. **Observation/Instance:** A single row or data point in a dataset.

5. **Label/Target:** The variable being predicted or analyzed in a machine learning problem (often the output).

### Statistical Concepts:

6. **Descriptive Statistics:** Techniques used to describe and summarize features of a dataset, like mean, median, variance, and standard deviation.

7. **Inferential Statistics:** Methods that infer insights or make predictions about a larger population based on sample data.

8. **Hypothesis Testing:** A statistical method to test assumptions or hypotheses about a population parameter.

9. **Correlation:** The measure of the strength and direction of the relationship between two variables.

### Machine Learning Terminology:

10. **Supervised Learning:** Machine learning approach where models learn from labeled data to make predictions or classifications.

11. **Unsupervised Learning:** Machine learning approach where models find patterns and structures in unlabeled data.

12. **Feature Engineering:** The process of creating new features or transforming existing ones to improve model performance.

13. **Overfitting and Underfitting:** Overfitting occurs when a model performs well on training data but poorly on new data; underfitting occurs when a model is too simple to capture the underlying patterns.

14. **Cross-validation:** Technique to assess the generalization performance of a model by splitting data into subsets for training and validation.

### Data Analysis and Visualization:

15. **Exploratory Data Analysis (EDA):** Initial analysis to understand the dataset's main characteristics through visualizations and summary statistics.

16. **Data Visualization:** Presenting data graphically to communicate patterns, trends, and insights effectively.

17. **Histogram:** A graphical representation of the distribution of numerical data.

### Tools and Technologies:

18. **Python/R:** Programming languages commonly used for data manipulation, analysis, and machine learning.

19. **Pandas:** Python library for data manipulation and analysis.

20. **Scikit-learn:** Python library providing machine learning algorithms and tools.

21. **Jupyter Notebooks:** Interactive environments for creating and sharing documents containing live code, visualizations, and narrative text.

Understanding these basic terms lays the foundation for delving deeper into the field of data science and effectively communicating within the data science community.

Data science vs data analytics: ✅

Data science and data analytics are related fields that involve working with data to extract insights, but they differ in scope, techniques, and objectives.

### Data Science:

1. **Scope:** Data science encompasses a broader spectrum, combining various disciplines like statistics, mathematics, computer science, and domain knowledge to analyze and interpret complex data sets. It involves the entire data lifecycle, from data collection and cleaning to modeling and deployment.

2. **Objective:** The primary goal of data science is to extract actionable insights and predictions from data, often using machine learning algorithms and statistical techniques. Data scientists focus on solving complex problems and building predictive models using programming languages like Python, R, or SQL.

3. **Techniques:** Data science involves advanced statistical analysis, machine learning, predictive modeling, data mining, and often works with large volumes of unstructured and structured data.

4. **Skills:** Data scientists typically require a strong background in programming, statistics, machine learning, and domain expertise to solve intricate problems and uncover hidden patterns in data.

### Data Analytics:

1. **Scope:** Data analytics is a subset of data science, primarily focusing on analyzing data to derive meaningful insights that can guide decision-making. It involves gathering, cleaning, and interpreting data to solve specific business problems.

2. **Objective:** The main objective of data analytics is to answer specific questions, identify trends, and provide insights based on historical data. It emphasizes descriptive and diagnostic analysis rather than predictive modeling.

3. **Techniques:** Data analytics involves descriptive statistics, exploratory data analysis, visualization, and often works with structured data to derive insights.

4. **Skills:** Data analysts require skills in data manipulation, visualization tools, statistical analysis, and domain knowledge to effectively interpret data and provide actionable recommendations.

### Summary:

- **Data Science** is a broader field that encompasses various techniques, including machine learning and statistical modeling, to uncover insights, build predictive models, and solve complex problems using data.

- **Data Analytics** is a subset of data science that focuses on analyzing data to provide insights and support decision-making, often involving descriptive and exploratory analysis of structured data.

While both fields overlap in their use of data, tools, and techniques, data science tends to be more comprehensive, involving predictive modeling and complex problem-solving, whereas data analytics primarily focuses on deriving insights and recommendations from historical data to drive business decisions.

How can data science be used to develop the country:✅

Data science offers numerous opportunities to contribute to the development of a country across various sectors by leveraging data-driven insights for informed decision-making, efficient resource allocation, and impactful policy implementation. Here are several ways data science can be utilized to foster development:

### 1. **Healthcare Improvement:**

- **Disease Prediction and Prevention:** Analyzing healthcare data to predict disease outbreaks, identify high-risk populations, and allocate resources effectively.

- **Precision Medicine:** Personalizing treatment plans and therapies by analyzing patient data, leading to more effective healthcare interventions.

- **Healthcare Infrastructure Planning:** Using data to optimize hospital resource allocation, staffing, and facility planning.

### 2. **Education Enhancement:**

- **Personalized Learning:** Applying data analytics to tailor educational content and teaching methods to individual student needs, enhancing learning outcomes.

- **Education Policy Design:** Analyzing educational data to inform policy decisions, improve school performance, and allocate resources efficiently.

### 3. **Economic Growth and Planning:**

- **Market Analysis and Forecasting:** Utilizing data science techniques to analyze market trends, consumer behavior, and industry patterns for informed economic decisions.

- **Optimizing Resource Allocation:** Applying data-driven insights to allocate resources effectively, foster innovation, and promote entrepreneurship.

### 4. **Infrastructure and Urban Development:**

- **Smart City Initiatives:** Using data science to optimize traffic flow, energy consumption, waste management, and public services in urban areas.

- **Infrastructure Planning:** Analyzing data to plan and prioritize infrastructure development, including transportation, utilities, and housing.

### 5. **Agricultural Advancements:**

- **Precision Agriculture:** Implementing data-driven techniques for optimizing crop yields, efficient resource usage, and sustainable agricultural practices.

- **Weather and Climate Analysis:** Utilizing data science for better climate predictions, mitigating natural disasters, and adapting to climate change.

### 6. **Government and Public Policy:**

- **Policy Formulation:** Leveraging data analytics to inform policy decisions in areas such as healthcare, education, transportation, and social welfare.

- **Transparent Governance:** Using data for better transparency, accountability, and citizen engagement in government initiatives.

### 7. **Natural Resource Management:**

- **Environmental Conservation:** Analyzing data to monitor environmental changes, wildlife conservation, and sustainable resource management.

- **Energy Efficiency:** Applying data science to optimize energy usage, develop renewable energy sources, and reduce environmental impact.

### 8. **Disaster Management and Response:**

- **Early Warning Systems:** Developing predictive models and systems to provide early warnings for natural disasters, facilitating better disaster preparedness and response.

- **Optimizing Relief Efforts:** Using data analytics to efficiently distribute resources and aid during emergencies and disasters.

Data science, when applied strategically across these sectors, can empower decision-makers, policymakers, and stakeholders with valuable insights that can lead to more effective planning, resource allocation, and sustainable development strategies for the country.

Life cycle of data science:✅

The data science life cycle encompasses the series of stages or steps involved in extracting insights and value from data. This cycle typically includes the following phases:

### 1. **Problem Definition:**

- **Understanding Business Objectives:** Identifying the problem or opportunity that data analysis aims to address and aligning it with the organization's goals.

- **Defining the Problem:** Formulating clear and specific research questions or problem statements to guide the data analysis process.

### 2. **Data Collection:**

- **Gathering Data:** Collecting relevant data from various sources, which can include databases, APIs, web scraping, surveys, or sensor data.

- **Data Cleaning and Preprocessing:** Cleaning the data to address issues like missing values, outliers, inconsistencies, and formatting discrepancies.

### 3. **Exploratory Data Analysis (EDA):**

- **Descriptive Statistics:** Performing statistical analysis and visualization to understand the basic characteristics of the data.

- **Identifying Patterns and Relationships:** Exploring the data to identify patterns, correlations, and potential insights.

### 4. **Feature Engineering and Selection:**

- **Feature Creation:** Creating new features or transforming existing ones to enhance model performance.

- **Feature Selection:** Identifying the most relevant and impactful features for model building and prediction.

### 5. **Model Building:**

- **Selecting Algorithms:** Choosing appropriate machine learning or statistical models based on the problem and data characteristics.

- **Model Training:** Training the selected models using the data to learn patterns and relationships.

### 6. **Model Evaluation:**

- **Validation:** Assessing model performance using various evaluation metrics and validation techniques to ensure accuracy and generalizability.

- **Fine-tuning:** Optimizing model parameters and configurations for better performance.

### 7. **Model Deployment:**

- **Putting Models into Production:** Integrating the trained models into applications, systems, or processes for real-world use.

- **Monitoring and Maintenance:** Continuously monitoring model performance, updating models, and ensuring they remain effective over time.

### 8. **Interpretation and Communication:**

- **Interpreting Results:** Understanding and explaining the insights and predictions generated by the models.

- **Visualization and Reporting:** Creating visualizations, reports, or presentations to effectively communicate findings to stakeholders.

### 9. **Feedback and Iteration:**

- **Feedback Loop:** Gathering feedback from stakeholders and users to refine models, strategies, or processes.

- **Iterating the Process:** Repeating the data science life cycle, incorporating new data, insights, or changes based on feedback and evolving business needs.

This cyclical nature of the data science process emphasizes the continuous improvement and refinement of models and strategies based on feedback, new data, and changing requirements. It's important to note that this cycle may vary in sequence or emphasis based on the specific project, industry, or organization.

Examples Real world scenarios (the ones we did in the DS presentations) ✅

Job requirements for a data scientist: ✅

The job requirements for a data scientist typically encompass a blend of technical skills, domain knowledge, and soft skills. Here's an overview of what is commonly expected from someone in this role:

### Technical Skills:

1. **Programming Languages:** Proficiency in languages like Python and/or R is essential. Understanding SQL for data retrieval from databases is also valuable.

2. **Statistics and Mathematics:** Strong understanding of statistical concepts like hypothesis testing, regression, probability, and mathematical modeling is crucial for data analysis and modeling.

3. **Machine Learning and Data Mining:** Experience with machine learning techniques and algorithms, such as classification, clustering, neural networks, and feature selection.

4. **Data Wrangling and Cleaning:** Ability to clean and preprocess data, handle missing values, outliers, and transform raw data into usable formats using tools like Pandas, dplyr, or SQL.

5. **Data Visualization:** Proficiency in data visualization libraries (Matplotlib, Seaborn, ggplot2, etc.) to create insightful and understandable visual representations of data.

6. **Big Data Technologies:** Familiarity with big data frameworks like Hadoop, Spark, or Flink for handling and processing large-scale datasets.

7. **Software and Tools:** Experience with tools such as Jupyter Notebooks, TensorFlow, PyTorch, scikit-learn, and other relevant software for analysis and modeling.

### Domain Knowledge:

1. **Industry Expertise:** Understanding the specific domain or industry the data scientist is working in (e.g., healthcare, finance, e-commerce) to tailor analyses and insights effectively.

2. **Business Acumen:** Ability to translate data insights into actionable business strategies and decisions, working closely with stakeholders to solve business problems.

### Soft Skills:

1. **Problem-solving:** Strong analytical and problem-solving skills to tackle complex issues using data-driven approaches.

2. **Communication Skills:** Effective communication is vital to convey complex findings and insights to both technical and non-technical stakeholders.

3. **Teamwork and Collaboration:** Capability to work in multidisciplinary teams, collaborate with other professionals, and share knowledge effectively.

4. **Curiosity and Continuous Learning:** Given the evolving nature of technology and data science, a passion for learning and staying updated with new techniques and tools is essential.

### Education and Experience:

- **Education:** A bachelor's or master's degree in fields like computer science, statistics, mathematics, data science, or a related field. Some roles may require a Ph.D. for research-oriented positions.

- **Experience:** Depending on the role, companies may seek candidates with a few years of relevant work experience in data analysis, machine learning, or a related field.

The specifics of job requirements can vary widely depending on the industry, company size, and the particular focus of the data science role within the organization. However, these skills and qualifications provide a strong foundation for success in a data scientist position.

Tools and software used by data scientists (python, R, Tableau, Excel, SQL, Power BI, pandas, Apache Hadoop, Apache spark): ✅

Data scientists use a variety of tools and software to collect, clean, analyze, and visualize data. These tools help in managing data effectively and extracting valuable insights. Some popular tools and software used by data scientists include:

1. **Programming Languages:**

- **Python:** Widely used for data analysis, machine learning, and statistical modeling. Libraries like Pandas, NumPy, SciPy, Matplotlib, and Scikit-learn are commonly used in Python.

- **R:** Another popular language for statistical analysis, data manipulation, and visualization, with a wide range of packages like dplyr, ggplot2, and caret.

2. **Data Manipulation and Analysis:**

- **SQL (Structured Query Language):** Essential for managing and querying relational databases.

- **Pandas:** Python library for data manipulation and analysis, offering data structures and tools for cleaning and preprocessing.

- **dplyr:** R package for data manipulation tasks like filtering, summarizing, and transforming data.

3. **Big Data Processing:**

- **Apache Hadoop:** Framework for distributed storage and processing of large datasets.

- **Apache Spark:** Provides a fast and general-purpose cluster computing system for big data processing.

- **Apache Flink:** Another framework for distributed stream and batch data processing.

4. **Machine Learning and Statistical Analysis:**

- **Scikit-learn:** Python library offering various machine learning algorithms and tools for modeling and evaluation.

- **TensorFlow and Keras:** Libraries for building and training neural networks and deep learning models.

- **PyTorch:** Another deep learning framework used for building neural network architectures.

- **Jupyter Notebooks:** Interactive environments for creating and sharing documents containing live code, visualizations, and narrative text.

5. **Data Visualization:**

- **Matplotlib:** Python library for creating static, interactive, and 3D visualizations.

- **Seaborn:** Built on top of Matplotlib, Seaborn provides more visually appealing statistical graphics.

- **ggplot2:** R package for creating elegant and complex data visualizations.

6. **BI and Analytics Platforms:**

- **Tableau:** User-friendly platform for data visualization and analytics.

- **Power BI:** Microsoft's business analytics tool for visualizing and sharing insights from data.

- **QlikView/Qlik Sense:** Platforms for data visualization, business intelligence, and data discovery.

7. **Data Cleaning and Preprocessing:**

- **OpenRefine:** Tool for cleaning and transforming messy data.

- **Trifacta:** Platform for data wrangling and preparation tasks.

8. **Cloud Platforms:**

- **Amazon Web Services (AWS), Microsoft Azure, Google Cloud Platform (GCP):** Cloud services offering various tools and resources for data storage, processing, and analysis.

Data scientists often choose tools based on project requirements, personal preferences, and the specific tasks they need to accomplish. These tools assist them in handling data efficiently and deriving meaningful insights to solve complex problems.

Research questions in the field in data science ✅

In data science, research questions often revolve around extracting insights, patterns, and actionable information from data. These questions guide the analysis process and help solve problems or discover new information. Here are some common types of research questions in data science:

1. **Descriptive Questions:**

- What are the key characteristics or trends in the dataset?

- How is the data distributed across different categories or groups?

- What are the summary statistics for the variables in the dataset?

2. **Diagnostic Questions:**

- What factors are contributing to a particular outcome or phenomenon?

- Are there any anomalies, outliers, or patterns that need further investigation?

- What is the root cause of a specific problem in the dataset?

3. **Predictive Questions:**

- Can we predict future outcomes based on historical data?

- What variables are most predictive of a certain event or outcome?

- How accurate are our predictions using different models or algorithms?

4. **Prescriptive Questions:**

- What actions or interventions can be recommended based on predictive models?

- How can we optimize a process or system to achieve better outcomes?

- What changes can be made to improve a specific metric or result?

5. **Exploratory Questions:**

- Are there any hidden patterns or relationships in the data?

- Can we identify clusters or groups within the dataset?

- What variables are most correlated with each other?

6. **Causal Questions:**

- What is the cause-and-effect relationship between variables?

- Can we establish causation based on observational or experimental data?

- How does changing one variable affect another in the dataset?

7. **Comparative Questions:**

- How do different groups or categories in the dataset compare to each other?

- What are the differences or similarities between subsets of the data?

- Are there significant differences in outcomes between different treatments or conditions?

These research questions serve as a starting point for data scientists to frame their analysis, select appropriate methodologies and techniques, and derive meaningful insights that can be used for decision-making, problem-solving, or further research. The choice of research question depends on the objectives of the analysis and the nature of the dataset.

Sources and types of data : ✅

Data can originate from various sources and can be classified into different types based on its nature and origin. Here are the primary sources and types of data:

### Sources of Data:

1. **Primary Sources:** Data collected firsthand for a specific purpose. It includes surveys, experiments, observations, interviews, and focus groups.

2. **Secondary Sources:** Data that already exists and is collected by someone else for their own purposes. This includes books, articles, official records, databases, and previously conducted research.

3. **Tertiary Sources:** Compilations or summaries of primary and secondary sources, such as encyclopedias, textbooks, or reference materials.

4. **Administrative Sources:** Data collected by organizations for administrative purposes, like customer databases, sales records, or financial reports.

5. **Publicly Available Sources:** Data available to the public, such as government publications, open data initiatives, public surveys, and data from NGOs or international organizations.

### Types of Data: ✅

1. **Quantitative Data:** Numerical data that can be measured and expressed using numbers. Examples include age, height, temperature, sales figures, etc. It can further be categorized into:

- **Discrete Data:** Countable and finite, like the number of students in a class.

- **Continuous Data:** Infinite and measurable, such as temperature or time.

2. **Qualitative Data:** Descriptive data that cannot be measured numerically. It describes qualities or characteristics and includes data like opinions, observations, and open-ended responses. It can be in the form of text, images, audio, or video.

3. **Categorical Data:** Represents categories or groups and can be further divided into nominal and ordinal data:

- **Nominal Data:** Data without an inherent order or ranking, such as colors or gender.

- **Ordinal Data:** Data with a natural order or ranking, like education levels or satisfaction ratings.

4. **Time-Series Data:** Data collected at different points in time, such as stock prices, weather data, or sales figures over a period.

5. **Spatial Data:** Data associated with geographic locations or maps, including GPS coordinates, addresses, or boundaries.

6. **Big Data:** Large volumes of data that require specialized tools and techniques for storage, processing, and analysis. It often includes structured, unstructured, and semi-structured data from various sources.

7. **Derived Data:** Information obtained by processing or manipulating raw data through calculations, transformations, or summarization.

Understanding the sources and types of data is crucial for selecting appropriate analysis methods and ensuring the relevance and reliability of insights drawn from the data.

Applicability of data ✅

Data finds applications across numerous fields and industries, playing a pivotal role in decision-making, problem-solving, and innovation. Here are some key areas where data is highly applicable:

1. **Business and Economics:** Data is extensively used for market analysis, forecasting, identifying consumer trends, optimizing supply chains, and making strategic business decisions. In economics, it helps in understanding economic indicators, forecasting financial trends, and assessing market dynamics.

2. **Healthcare and Medicine:** Data aids in patient diagnosis, treatment planning, drug development, and clinical trials. It facilitates personalized medicine, disease prediction, and the management of public health initiatives.

3. **Technology and Information Systems:** In tech, data drives innovation, powering artificial intelligence, machine learning, and natural language processing. It's vital for cybersecurity, database management, and software development.

4. **Science and Research:** In various scientific disciplines, data enables researchers to analyze experimental results, model complex systems, and validate theories. It's fundamental in fields like astronomy, biology, physics, and environmental science.

5. **Finance and Banking:** Data analytics is crucial in risk assessment, fraud detection, algorithmic trading, and customer relationship management in the finance sector.

6. **Education:** Educational institutions use data to track student performance, assess teaching methodologies, and personalize learning experiences through adaptive learning platforms.

7. **Government and Public Policy:** Data aids policymakers in making informed decisions by analyzing social, economic, and demographic trends. It's used in urban planning, public safety, disaster management, and policy evaluation.

8. **Marketing and Advertising:** Data-driven marketing involves customer segmentation, targeting, and personalized advertising based on consumer behavior and preferences.

9. **Agriculture and Environmental Sciences:** Data assists in precision agriculture by optimizing crop yield, managing resources efficiently, and monitoring environmental changes.

10. **Social Sciences and Humanities:** Data analysis techniques are increasingly applied in fields like psychology, sociology, anthropology, and history to understand human behavior, social trends, and cultural patterns.

In essence, data is versatile and applicable across diverse domains. Its utility lies in its ability to provide insights, patterns, and correlations that drive informed decision-making and innovation in almost every aspect of human endeavor.

Methods to acquire the data: ✅

Acquiring data involves collecting information from various sources to build datasets for analysis. Several methods are used to acquire data:

1. **Surveys and Questionnaires:** Conducting surveys or questionnaires to gather specific information from individuals or groups. These can be administered in person, via mail, phone, or online.

2. **Observational Studies:** Collecting data by observing and recording events, behaviors, or phenomena. This method involves direct observation without influencing the subjects.

3. **Experiments:** Controlled studies where researchers manipulate variables to observe their effect on outcomes. This method helps establish causation between variables.

4. **Secondary Data Sources:** Utilizing existing data collected by other researchers, organizations, government agencies, or databases. This includes data obtained from books, articles, official records, or public datasets.

5. **Web Scraping:** Extracting data from websites by using automated tools to gather information available online. This method requires adherence to ethical and legal guidelines regarding data usage and web crawling.

6. **Sensors and Internet of Things (IoT):** Collecting data from various sensors and IoT devices that capture information about physical or environmental conditions.

7. **Social Media and Online Platforms:** Gathering data from social media platforms, forums, and other online sources using APIs (Application Programming Interfaces) or scraping tools.

8. **Interviews and Focus Groups:** Conducting structured or unstructured interviews and focus group discussions to gather qualitative data by directly interacting with individuals or small groups.

9. **Audio and Video Recordings:** Recording audio or video data for qualitative analysis or extracting information from these recordings using specialized tools.

10. **Mobile Apps and Devices:** Collecting data through mobile applications or devices that track user behavior, location, health metrics, or other personalized information.

The choice of data acquisition method depends on various factors such as the research objectives, available resources, ethical considerations, the nature of the data required, and the target population. Researchers often use a combination of methods to obtain comprehensive and reliable datasets for analysis. Ethical considerations, privacy, and data security are critical aspects to consider when acquiring data from any source.

Types of analysis: ✅

-- EDA (EXPLORATORY DATA ANALYSIS): Analyzing data sets to summarize their main characteristics, often uncovering relationships and patterns.

the techniques used are:Data visualization, correlation analysis, clustering, principal component analysis (PCA).

-- DESCRIPTIVE DATA ANALYSIS: this is about describing and summarizing the data to discover the basic features, patterns and charcteristics.

this is done by using techniques like data visualization (pie charts, histograms, and box plots), frequency distribution, and summary statistics.

-- PREDICTIVE ANALYSIS: Using historical data to forecast or predict future outcomes or trends. The techniques used here are Machine learning algorithms (e.g., regression, classification, time series forecasting).

-- DIAGNOSTIC ANALYSIS: Identifying reasons behind certain outcomes or patterns by investigating cause-and-effect relationships in data.

Techniques used here are Root cause analysis, A/B testing, decision trees.

-- Prescriptive Analysis:Recommending actions or strategies based on analysis to optimize or improve future outcomes.

techniques used are : Optimization algorithms, simulation modeling, recommendation systems.

Key terminologies in programming languages (variables, functions,control structures, data types, modules, libraries, lists, tuples, file handling, dictionaries, ploting, data manipulation, visualization) ✅

How to Rectify data: (here we are basically cleaning the data upfront, Properly preprocess data by: ✅

-- handling missing values using the imputation [here by replacing missing values using the mean, median etc] or dropping method [droping the data which cannot be imputed accuratelly],

-- Handling Duplicates [detection and removal],

-- Outlier Detection and Treatment,

-- Data Normalization or Standardization [use apropriate datatype].)) ✅

How to clean data ✅

How to increase accuracy of a model:

-- Use techniques like k-fold cross-validation to ensure the model generalizes well to new data and to minimize overfitting.

-- Combine multiple models (like Random Forests or Gradient Boosting) to create a stronger, more accurate prediction.

-- Sometimes, increasing the quantity of quality data can significantly improve model performance.

-- cleaning the data upfront (Properly preprocess data by handling missing values, scaling features, or encoding categorical variables appropriately.)

-- Deepen your understanding of the domain and the dataset to make more informed decisions about feature selection and model design.

Data formats

How can data science be used in Ucu (student performances check, course improvement and optimization of the resources provided by the university like classes, material etc), in a movie center we can talk about audience insights or preferences, attendance patterns, and demographic data to optimize scheduling and calendar (this is a personal point of view) ✅

Python skills ✅

Online platform to create a model (Jupyter notebook, google collab) ✅

Be able to import datasets (first we upload the file inside collab using the file button in collab at the left, then after uploaded the excel or csv file, we can copy its path, then we go in the code and do this: | df = pd.read_csv('[copy the path here]') | then to see the content inside the data frame, we just do | df.head() which will print only the first 5 records from the dataset to show that it can be accessed successfully | ✅

Be able to create your own datasets (considering that we have a data set stored somewhere) ✅

Learn how to visualize data -boxplot, histogram,pie chart ✅

Know the necessary libraries (pandas, sklearn.model_selection,sklearn.ensemble,sklearn.metrics, geopandas,matplotlib.pyplot) ✅

Export your work -learn