Collection of some programming assignments completed for Practicum's Data Scientist professional training program.
| Project Name | Notebook | Description | Dependencies | Sprint Number |
|---|---|---|---|---|
| classifying_churn | classifying_churn.ipynb | Used machine learning and data balancing techniques to create a predictive model for churn producing an AUC-ROC higher than the target AUC-ROC (0.93 versus goal of > 0.88). | NumPy, Pandas, matplotlib, seaborn, math, time, functools, re, IPython.display, sklearn, catboost, lightgbm, xgboost, random, sys | 15 (final) |
| computer_vision | computer_vision.ipynb | Use supplied photos to build and test a regression model to predict age on a continuous scale. | Pandas, Seaborn, matplotlib, tensorflow, keras | 14 |
| ml_for_text | ml_for_text.ipynb | Train a model for classifying positive and negative reviews with a F1 score of at least 0.85. | NumPy, Pandas, matplotlib, seaborn, re, math, tgdm | 13 |
| time_series | time_series.ipynb | Use historical data on taxi orders to predict peak hours using RMSE as the metric. | NumPy, Pandas, matplotlib, sciPy, seaborn, time, math, statsmodels, sklearn, IPython, sys, catboost, lightgbm, xgboost | 12 |
| numerical_methods | numerical_methods.ipynb | Generate a model that predicts the value of a car based on historical data (such as trims, prices, milage, technical specs) | NumPy, Pandas, matplotlib, seaborn, time, math, sklearn, random, sys, catboostregressor, decisiontree | 11 |
| linear_algebra | linear_algebra.ipynb | Use ML to categorize customers, identify customers likely to receive an insurance benefit, and use data masking. | NumPy, Pandas, math, seaborn, matplotlib, sklearn, IPython, sys | 10 |
| ml_in_industry | ml_in_industry.ipynb | Find the ML model that best predicts the two target values given the predictor variables present for gold extraction from ore. | NumPy, Pandas, math, seaborn, matplotlib, sklearn, random, sys | 9 |
| ml_in_business | ml_in_business.ipynb | Use machine learning and boostrapping to select a region with the highest profit margin given a selection of masked features. | NumPy, Pandas, math, seaborn, matplotlib, sklearn, scipy, random, sys | 8 |
| supervised_ml | supervised_ml.ipynb | Predict customer churn for a bank. | NumPy, Pandas, math, matplotlib, sklearn, random, sys | 7 |
| machine_learning | machine_learning.ipynb | Creat a ml model that recommends an appropriate plan based on data about the behavior of subscribers who've already switched (with accuracy > 75%) | NumPy, Pandas, sklearn, sys | 6 |
| sql | sql.ipynb | Identify top neighborhoods in terms of drop-offs for a new ride sharming company. | NumPy, Pandas, matplotlib, seaborn, scipy | 5 |
| hypothesis_testing | hypothesis_testing.ipynb | Preliminary analysis of platform, genre, and ESRB ratings to determine any patterns that influence sales. | NumPy, Pandas, matplotlib, sciPy, seaborn | 4 |
| statistical_data_analysis | statistical_data_analysis.ipynb | Analysis of phone plans, revenue, and retetion to produce recommendations for the marketing team. | NumPy, Pandas, matplotlib, sciPy | 3 |
| exploratory_data_analysis | exploratory_data_analysis.ipynb | Use EDA to study data collected over the last few years from online advertisements and determine which factors influence the price of a vehicle. | NumPy, Pandas, matplotlib | 2 |
| credit_scoring | 15_credit_scoring_sprint_1.ipynb | Create a credit score for potential customers for a loan examining marital status and number of children as features. | NumPy, Pandas | 1 |
Authors
Renee Raven
License
This project is licensed under the MIT License - see the LICENSE file for details