You're about to create your best presentation ever

Data Science Project Presentation Background

Create your presentation by reusing one of our great community templates.

Data Science Presentation

Transcript: Data Science Project Purpose Imagine you are asked to settle in a different city and you just don't have enough information about the city. What will you do, how will you choose the area that you want to live in? Description The problem statement revolves around a boy named Siddhartha. Siddhartha is a national level badminton player. Siddhartha got placed in Toronto, Canada but he's worried about his badminton career. He's not aware of the city and wants know the best area in the city so that he can also focus on his badminton as well. Let's see how our project helps him out! Objectives In order to solve the problem, we came up with our project, "The Battle of Neighbourhoods". The project divides the city in clusters on the basis of their longitude & latitude and ultimately helps you to find your ideal residential area! Collect and clean the data Analyze the data Visualize the data Collect/Clean Web Scraping using BeautifulSoup and getting coordinates using geopy Foursquare API to explore neighbourhoods Creating map and filtering data Data Collection & Cleaning The first step is to collect data and clean it. We use a technique called Web Scraping to get our data. After which we create the map of the city and filter the data. At the end, Foursquare API is used to explore neighbourhoods. KMeans Clustering KMeans clustering divides the data into K non-overlapping subsets or clusters without any cluster internal structure. It is an unsupervised algorithm. Distance of samples from each other is used to shape the clusters. There are two approaches to choose the centroids. Assign each customer to the closest center. Form a distance matrix. Iterative algorithm Not necessarily the best possible outcome. Visualize Vizualization Examining Clusters At the end, we need to visualize our findings in the best possible way. With the help of folium library, we create the map and then specify each cluster with a colour Finally, we examine each and every cluster one by one and by seeing the most common venue, we suggest the best residential area to the person. Team Manmohan SIngh Abhinav Ruhela Abhijeet Saxena We are a team of three members, and each one of us believes that learning data scince is the ultimate goal while the project is just a by-product! Resources IBM Cognitive Class IBM Cognitive Labs Towards Data Science In this project, we only consider one factor i.e. latitude and longitude of a specific area, there are other factors such as connectivity of the area and income of person that could influence the location decision of a finding a residence. However, to the best knowledge of this researcher such data are not available to the neighbourhood level required by this project. Future research could devise a methodology to estimate such data to be used in the clustering algorithm to determine the preferred locations for someone to settle in a specific city. In addition, this project made use of the free Sandbox Tier Account of Foursquare API that came 45 with limitations as to the number of API calls and results returned. Future research could make use of paid account to bypass these limitations and obtain more results. Foursquare What more can be done?

Data Science Presentation

Transcript: Overview Predicting Breast Cancer Survival and Treatment Outcomes Using Clinical and Genetic Data Goal: Develop predictive models for breast cancer outcomes using METABRIC dataset. Dataset: 1,980 primary breast cancer samples including demographics, tumor characteristics, treatment types, survival outcomes, mRNA expression levels, and gene mutations. Methodology: Data acquisition and preprocessing (cleansing, EDA, dimensionality reduction). Gene expression analysis to identify potential biomarkers. Machine learning algorithms: Logistic Regression, Random Forest, SVM. Focused on the top 20 genes with the most patients. Social or Ethical Implications Privacy and Data Security: Ensure protection of patient data. Ethical Use: Avoid discrimination or stigmatization based on genetic profiles. Access Disparities: Ensure equal access to personalized treatments for all patients. Informed Consent: Maintain transparency and trust with patients. Bias in Models: Address biases to ensure fair and accurate predictions for all groups. Runeem Al-Abssi, Avie Burris, Camille Anderson Findings Figures Recommendations Significant Genes: rad51c, psen2, jag1, and hdac1 correlated with breast cancer prognosis. Gene Expression Impact: Variability in gene expression levels affects survival outcomes. Treatment Response: Varied based on genetic and clinical profiles. Complex Interactions: Between gene mutations, expression levels, tumor size, and patient age. Conclusion Personalized Treatment Plans: Tailor treatments based on genetic and clinical profiles. Targeted Gene Therapy: Investigate genes like rad51c, psen2, jag1, and hdac1 for new treatments. Enhanced Predictive Models: Incorporate more genomic data and advanced algorithms. Clinical Decision Support: Use predictive models in clinical systems to aid treatment decisions. Success: Demonstrated the usefulness of machine learning in predicting breast cancer outcomes using integrated clinical and genetic data. Key Insights: Identified significant biomarkers and treatment factors to support personalized treatment strategies. Impact: Potential to enhance prognostic accuracy and advance precision medicine in oncology. Future Work: Incorporate additional genomic data and explore more advanced machine learning models to further refine predictions and improve clinical decision-making. Goal: Improve patient care and outcomes through better understanding and tailored treatment approaches.

Data Science Presentation

Transcript: Data Scientist Interview What I Learned The Basics Dr. Singh started out at The Fed Economic Research Data Cleaning Linear and Logistic Regression Went back to school and got her doctorate in data science Now works at google as a data scientist with the YouTube Comments team The Interview Interview Process 1. Screening Call with an HR Rep. to determine the best role for you (could be different than what you applied for) 2. Technical Interview to cover your general statistical and coding knowledge (there are 4 in total) 3. Behavioral interview to asses the parts of you that don't have to do with your technical ability 4. Then everything you've done so far goes through multiple committees to make sure everything's up to snuff 5. You then get to interview other hiring managers to figure out what team you want to work with Dr. Singh said the whole process took 8 week Day To Day Day to Day For Dr. Singh her job is unique in a way that her department is full of data scientists but they all work with different product segments She works primarily with the YouTube comments team where she works closely with the software engineers and product managers Her day to day mainly contains meetings with the software engineers and product managers of the YouTube comments team to determine what they need while the rest is spent coding She best describes it as being an internal consultant who does what ever they need done, small, medium, and large, when it comes to data science Languages and Technologies Commonly Used Technologies It mainly depends on what team shes working with SQL, R, Python with a little bit of C++ are all used. Data scientists don't need to know all of these but at least at google SQL is needed because its the primary way they interact their databases Its hard to get as much support for R because only 50 of the 3000 people working with YouTube are data scientists. Dr. Singh says she has a preference for R for data analysis but is trying to move towards python for the reason stated above. Knew most of the technologies going in (had to touch up on C++ and SQL) but Google has dedicated time every quarter for learning on the Job Favorite Project Favorite Project? One of her first projects The comments team had a metric they wanted to use but the data for it was extremely noisy Dr. Singh developed a method that improved the usable data by 300%. She was able to fully implement her work in a way that it was essentially plug and play for the comments team to use. It required no changes to their current codebase. The reason she enjoyed it so much was the fact that she got to use a bunch of different languages, learned a bunch of new stuff, and in the end got to wrap it up in a nice neat package that was actually useful. Current and Future Projects Recent Projects A survey after you watch a video that lets you pick between and rate 2 different comments as to which one is more relevant. Researching the correlation between Engagement signals and user satisfaction Currently working on how to detect brigaiding and notify the creator as its happening so they can disable comments and protect themselves. This involves determining what metrics are indicative of brigaiding (dislikes, mass comments, etc) Random Information Fun Facts and Random Information Her office has a slide in it to get down stairs Google hosts YTF (YouTube Fridays) where you can talk with coworkers outside of a work environment as well as talk with the YouTube CEO in a relatively relaxed environment. She also mentioned there is awesome live music. She's only had to work outside of work once and her boss was mad that it even happened at all. She said while its extremely uncommon for data science stuff to be deadline focused but it might be a little different for software engineers. "When getting your PHD you learn how to learn" Took a shotgun approach to applying for jobs (Chase Bank, Post Doc at Yale, Social Policy Think Tank, Lawrence Liver more National Lab, and many more) Advice for younger self "Stop trying to plan so much, just let go a bit, everything will be okay".

Data Science Presentation

Transcript: PLAN Data Scientist 2019 Sean F. Larsen Data Science Plan Creation Plan Creation Education Programming Skills Course Projects Tasks Education Education Statistics Statistics Basics Statistics Statistical Methods Regression Analysis Probability and Distribution Theory Statistical Regression and Inference Analysis Analysis Predictive Analysis Inferential Analysis Causal Analysis Mechanistic Analysis Decision Making Data Skills Data Skills Subject Selection Data Mining Data Cleaning Data Exploration Data Presentation Data Presentation Data Visualization Story Telling With Data Programming Programming Courses Courses Projects Projects 5 Types of Data Science Projects 5 Types Importing data Joining multiple datasets Detecting missing values Detecting anomalies Imputing for missing values Data quality assurance Exploratory Data Analysis Exploratory Data Analysis Ability to formulate relevant questions for investigation Identifying trends Identifying correlation between variables Communicating results effectively using visualizations Interactive Data Visualization Interactive Visualization Including metrics relevant to your customer’s needs Creating useful features A logical layout (“F-pattern” for easy scanning) Creating an optimum refresh rate Generating reports or other automated actions Reason why you chose to use a specific machine learning model Splitting data into training/test sets Selecting the right evaluation metrics Feature engineering and selection Hyperparameter tuning Machine Learning Machine Learning Know your intended audience Present relevant visualizations Don’t crowd your slides with too much information Make sure your presentation flows well Tie results to a business impact Communication Communications First 5 Projects First 5 Continued Work Continued Work Tasks Tasks Data Science Resume Data Science LinkedIn Profile Apply for Jobs Start a Blog Update My GitHub Account Update My Pinterest Account

Background Data

Transcript: Concept Map 4 Acetaminophen/1000mg/q6h/oral/for pain Bisacodyl/10mg/once a day/rectal/for constipation d/t required bedrest Enoxaparin/36mg/q12h/sub-q/to prevent clot formation d/t bilateral below the knee casts requiring bed rest Fluoxetine/30mg/nightly/oral/to treat depression Labs & Results Age: 15 Allergies: NKA Medical Diagnosis/Reason for admission: Bilateral ankle fracture d/t attempted suicide jump out of 2nd story windwo after ingesting "handful of corcidin." Reported loss of consciousness upon fall. Pertinent medical and surgical history: H/o depression, anxiety. Suicide attempt in March. Raped a few years ago-mom not aware (does not want mom to know). This will affect patient care and education because if the patient lacks good mental health, she is less likely to adhere to given instructions and more likely to continue to perform self-inflecting harm. Birth data: No data available. Erickson's Developmental Stage: Identity vs Role Confusion This is currently affecting the patient because she is trying to find where she fits in the world and displays confusion as to what her role is in this moment in time. Psychologist Erik Erikson said that this exploration is part of a psychosocial crisis, where adolescents have to find themselves otherwise if they stay in role confusion, they will feel dissatisfied and have trouble figuring out what they want out of life- which is what this patient has struggled to find. Background Data Physical Assessment Medications (Name/Dosage/Frequency/Route/Rationale) Nursing Diagnosis 1. Risk for self-harm r/t previous history of prior suicide attempt Goals: -Pt will not harm self during duration of hospital stay and upon follow-up visit -Pt will maintain connectedness in relationships for 2 weeks following discharge Interventions: -Be alert for warning signs of suicide: making statements such as, “I can’t go on,” “Nothing matters anymore,” “I wish I were dead”; becoming depressed or withdrawn; behaving recklessly; getting affairs in order and giving away valued possessions; showing a marked change in behavior, attitudes, or appearance; abusing drugs or alcohol; suffering a major loss or life change. -Question family members regarding the preparatory actions mentioned.Communicate the degree of risk to family and caregivers; assess the family and caregiving situation for ability to protect the client and to understand the client’s suicidal behavior. Provide the family and caregivers with guidelines on how to manage self-harm behaviors in the home environment.. -Before discharge from the hospital, ensure that the client’s parent has a supply of ordered medications, has a plan for outpatient follow-up, has a caregiver who understands the plan or is able and willing to follow the plan, and has the ability to access outpatient treatment. 2. Powerlessness r/t physical limitations and dependence on others to meet basic needs Goals: -Pt will demonstrate increased feelings of control over his/her situation -Pt will participate in self-care activities within physical limitations and prescribed activity restrictions Interventions- -Assess for behaviors that may indicate feelings of powerlessness (e.g. verbalization of lack of control over self-care or current situation, anger, irritability, passivity, lack of participation in self-care or care planning). -Evaluate client's perception of current situation, strengths, weaknesses, expectations, and parts of current situation that are under his/her control. Correct misinformation and inaccurate perceptions and encourage discussion of feelings about areas in which there is a perceived lack of control. -Support realistic hope about probability of future independence and ability to resume usual roles and lifestyle. -Include client in the planning of care, encourage maximum participation in the treatment plan, and allow choices whenever possible to promote a sense of control. -Encourage significant others to allow client to do as much as he/she is able so that a feeling of independence can be maintained. Ackley, B., & Ladwig, G. (2014). Nursing diagnosis handbook. Maryland Heights, Mo.: Elsevier. All immunizations are up to date. Pt denied flu vaccine before discharge. From 10/25- last day they were recorded -RBC: 3.42 (4.1-5.3)/ Low d/t recent bilateral ankle surgery and current Lovenox medication -Hematocrit: 27.7% (35-45)/ Low d/t recent bilateral ankle surgery and current Lovenox medication -Hemoglobin: 9.0 (12-15)/ Low d/t recent bilateral ankle surgery and current Lovenox medication -Platelets: 598 (150-450)/ High d/t inability to excercise as a result of bilateral below the knee casts requiring bed rest Social Work Services: Mom wanted to be called by a social worker because she had questions regarding discharge since she will not make it before then. -Pulse: 89 bpm/ 2+(Normal)/ Location- Radial, RUE -O2: 99% intermittent, room air -RR: 17 per min -BP: 109/53 (L arm sitting) -Temperature: 36.9 C -Pain: 0/10 (Numeric Scale) -General

Now you can make any subject more engaging and memorable