Home / Blog / Data Science / High Level Project Management – Data Science

High Level Project Management – Data Science

December 10, 2024
25

Meet the Author : Mr. Bharani Kumar

Bharani Kumar Depuru is a well known IT personality from Hyderabad. He is the Founder and Director of AiSPRY and 360DigiTMG. Bharani Kumar is an IIT and ISB alumni with more than 17 years of experience, he held prominent positions in the IT elites like HSBC, ITC Infotech, Infosys, and Deloitte. He is a prevalent IT consultant specializing in Industrial Revolution 4.0 implementation, Data Analytics practice setup, Artificial Intelligence, Big Data Analytics, Industrial IoT, Business Intelligence and Business Management. Bharani Kumar is also the chief trainer at 360DigiTMG with more than Ten years of experience and has been making the IT transition journey easy for his students. 360DigiTMG is at the forefront of delivering quality education, thereby bridging the gap between academia and industry.

Data Collection

Primary Data Sources – Data collected at that moment – Surveys / Experiments
- Costly
- Time-consuming / Low quality
- Get the exact variable
Secondary Data Sources – Data which is collected beforehand
- Quick access to data
- Free of cost
- Need not have data of interest

Want to learn more about data science? Enroll in the Best Data Science courses in Chennai to do so.

Data Cleansing / Data Preparation / Exploratory Data Analysis / Feature Engineering

Data Cleansing / Data Preparation
- Outlier Analysis / Treatment – 3R (Rectify, Retain, Remove)
- Missingness of data – Imputation – Mean, Median, Mode, Regression, KNN
- Standardization (X-Min(X)/Range(X) / Normalization (X-Mu/Sigma)) – Unitless and Scale Free
- Discretization / Binning / Grouping
- Transformation (log, exp, etc.)
  - Non-linear
  - Non-normal
  - Heteroscedasticity – unequal variance
  - Collinearity
- Dummy variable creation – One hot encoding
Exploratory Data Analysis

Earn yourself a promising career in data science by enrolling in the Data Science Classes in Pune offered by 360DigiTMG.
- First-moment business decision / Measures of central tendency
  - Mean, Median, Mode
- Second-moment business decision / Measures of dispersion
  - Variance, Standard Deviation, Range
- Third-moment business decision – Skewness
- Fourth-moment business decision – Kurtosis
- Graphical Representation
  - Univariate
    - Box Plot
      - Primary purpose – Identify outliers
      - Secondary purpose – Identify shape of distribution
    - Histogram
      - Primary purpose – Identify Shape of distribution
      - Secondary purpose – Identify outliers
    - Q-Q plot – Data are normal or not
  - Bivariate
    - Scatter plot
      - Primary purposes
        
        Direction-Positive, Negative, no correlation
        
        Strength – Strong, moderate, weak – Subjective; Objective – correlation coefficient; r: -1 to +1; |r| > 0.85; |r| < 0.4
        
        Linear or Non-linear / Curvilinear
      - Secondary purposes
        
        Scatter plot
        
        Primary purposes
        
        Clusters
        
        Outliers
        
        Feature Engineering / Feature Extraction – Using your given variables, try to apply domain knowledge to come up with more meaningful derived variables
        
        Feature Selection -> Decision Tree (Information Gain), Random Forest (Variable Importance plot), Hypothesis testing, Lasso regression, Ridge regression

Data Mining (Cross-Sectional)

Supervised Learning / Machine Learning / Predictive Modelling (Y known)
- Regression Analysis (Interpret the parameters)
  - Y= Continuous -> Linear Regression
  - Y = Discrete (2 categories) -> Logistic Regression
  - Y = Discrete (> 2 categories) -> Multinomial / Ordinal Regression
  - Y = Count -> Poisson / Negative Binomial Regression
  - Excessive Zero – ZIP / ZINB / Hurdle
- KNN
- Black Box Techniques (No interpretation exists)
  - Neural Networks
  - SVM
- Ensemble Techniques
  - Stacking
  - Bagging(Random Forest)
  - Boosting (Decision Tree)
Looking forward to becoming a Data Scientist? Check out the Data Science Course and get certified today.

Unsupervised Learning (Y unknown)
- Clustering / Segmentation – Reduce the rows
  - K-Means / non-hierarchical – Upfront determine the # of clusters – Scree plot / Elbow curve
  - Hierarchical / Agglomerative – Dendrogram
  - DBSCAN
  - OPTICS
  - CLARA
  - K-medians / K-Medoids / K-modes
- Dimension Reduction – Reduce the columns
  - PCA, Factor Analysis
  - SVD
- Association Rules / Market Basket Analysis / Affinity Analysis
  - Support
  - Confidence
  - Lift Ratio > 1 => Antecedent and Consequent have strong association
- Recommender Systems
- Network Analytics
  - Degree
  - Closeness
  - Betweenness
  - Eigenvector
  - Page Rank
- Text Mining & NLP
  - BoW
  - TDM / DTM
  - TF / TFIDF
Also, check this Data Science Institute in Bangalore to start a career in Data Science.

Watch Free Videos on Youtube
Forecasting / Time Series
- Model-Based Approaches
  - Trend
    - Linear
    - Exponential
    - Quadratic
  - Seasonality
    - Additive
    - Multiplicative
- Data-Based Approaches
  - AR
  - MA
  - ES
    - SES
    - Holts
    - HoltWinters