1.
1. Model : SVM
2. EDA : Exploratory Data Analysis
3. Data Cleaning: Removing outliers
4. Data Transformation: StandardScaler and MinMaxScaler
5. Hyperparameter Tuning: GridSearchCV
6. Data Split: 70:30
7. 5 different sets of experiments with different combinations:
8. Results of each experiments

…tra code for other fixes

1. Changed helpers.py file
2. Updated python notebook to add the description of 70/30 ratio
3. Changed the function call train_svm in python notebook
4. Changed function call train_svm_with_hyperparameter_tuning

1. Changed helpers.py file
2. Updated python notebook to add the description of 70/30 ratio
3. Changed the function call train_svm in python notebook
4. Changed function call train_svm_with_hyperparameter_tuning

it can now be seen by double clicking the image

1. Fixed transformation code in helpers.py
2. Fixed comment in notebook "train-n-test-model-for-vehicle-recognition-from-silhouette-II"

1. Fixed comment in notebook "train-n-test-model-for-vehicle-recognition-from-silhouette-I"

1. Fixed comment in notebook "train-n-test-model-for-vehicle-recognition-from-silhouette-I"

…ogistic Regression (#12)

* Data Loaded from vehicles.csv

* Data visulaization and training model with ifferent algorithms

* Evaluation of model is done.

* Changed model from Logistic Regression to Support Vector Machine

At first attempt i used three differnet models but Logistic Regression , Support Vector Machine and Decision Tree, and the overall accuracy with LR was better than any other but with changing validation parameters in SVM classification , model accuacy increased from 82% to 88%.

* Delete train and test model-checkpoint.ipynb

* Changed file named.

* all python modules were added

* docstrings were added

* labels added in confusion matrix

* Histogram colors were changed into single color

* solved histogram issue

* Update modules.py

* changes made in histogram

* Update modules.py

* sorted histogram

* Update modules.py

* labels were added for confusion matrix

* Python Custom Modules were added

* Update Vehicle_Classifier.ipynb

* Update modules.py

* Update modules.py

* Update modules.py

* added labels in confusion matrix

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Requested Changes were made

* Update modules.py

* change categorical data into numerical data

* change areguments in LR model

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Requested changes were made

* Update modules.py

* Update modules.py

* Update modules.py

* Delete Untitled.ipynb

* code formatted using python Black

* Requested changes were made

* shifted classifier's code from modules.py to ModelEvaluation.py

* removed learning curves from file

* added function for model evaluation in Model Evaluation file

* updated svm and lr

* added comments

* added doc strings

* Update ModelEvaluation.py

* Update ModelEvaluation.py

* Update Vehicle_Classifier.ipynb

* Update modules.py

* added descriptions

* added interpretations of visualization

* First attempt on vehicle data with a random forest calssifier

* minor changes

* Comparative model evaluation for vehicle dataset

* first attempt for implementing task 7

* fixes #8

* fixes #4, attempt 1

* implemeneted all change requests

* formatted code for all helper files

* minor fix

* Update README.md

* Update README.md

* Update README.md

* EDA and wine classification model with SVM.

Did exploratory data analysis and built an svm model that yielded with an accuracy of 77.6%

* Changed reported value of true positives.

Made a mistake reporting the value of true positives.

* Update winequality.ipynb

* Changed notebook directory and modified the model

Moved the notebook from the PRESC folder to another folder inside dev.

I also worked on the wine recommendation model, dealing with imbalance and improving on its performance.

* Corrected some spelling errors in the documentation.

* Updated the README

… points in train_features (#42)

* added function for importance_score

* added example for importance_score, fixes #8

* minor changes in graph plotting

…of classes (#86)

* Contribution to issue #2

* Eliminació de l'arxiu de prova

* Eliminació de l'arxiu de prova

* Fixed axes when not numbers and removed superfluous function.

* Initial commit to Issue #7 Visualization of missclassifications.

* Adding explanatory graphs for the notebook regarding Issue #7

* Better graph to illustrate option 'hits-fails'.

* KNN model trained and tested on generated.csv dataset

* Hyperparameter tuning and cross validation implemented

Classification of wine quality with random forest

* first commit

* models for defaults dataset

* optimized models

* final

* visual for eeg

* code restructured

* #3 data-split space mapped

* tabulated relation btw k and evaluation metrics

* gain-lift charts of models

* interprtation added

Added detailed instructions on setting up and activating the environment. This will be helpful for people who are new to git, GitHub and conda environment.

* visual for eeg

* code restructured

* #3 data-split space mapped

* fixes issue3

* studied data splits for all classifiers

* added graph in the loop

* docstrings added

* validation sets added

* formatting

* evaluated all classifiers

* compared models

* result added

* First attempt on vehicle data with a random forest calssifier

* minor changes

* Comparative model evaluation for vehicle dataset

* first attempt for implementing task 7

* fixes #8

* fixes #4, attempt 1

* updated missclassification graph and brokedown functions

* fixed code formatting issues and  removed extra file

…ethod (Forests of Randomized Trees) on defaults.csv (#53)

* adds .ipynb, .py for defaults.csv and updates environment.yml

* Update defaults_modules.py

added new line at the end of file

* makes requested changes

* adds a module to visualize misclassification and tests it on winequality.csv

* adds description and details for results obtained

* Add Logistic Regression Model for Winequality dataset

Signed-off-by: SanchiMittal <[email protected]>

* Add python modules

Signed-off-by: SanchiMittal <[email protected]>

* Minor Changes

* Add Black Formatting

* initial contribution

* initial updated

* KNN model trained and tested on generated.csv dataset

* Effect of split ratio on performance

* Hyperparameter tuning and cross validation implemented

* Black formatting applied

Co-authored-by: mlopatka <[email protected]>

* KNN model trained and tested on generated.csv dataset

* Hyperparameter tuning and cross validation implemented

* Relevance of a training datapoint to the performance of a trained model evaluated

Co-authored-by: mlopatka <[email protected]>

* For #5: Calibration plot

* reformatted calibration_plot using black

* improve function code for better readability

* renamed function calibration_plot to plot_calibration_curves, added explanatory text and curve interpretation in example notebook, reformatted notebook

…nce score (#67)

* KNN model trained and tested on generated.csv dataset

* Effect of split ratio on performance

* Hyperparameter tuning and cross validation implemented

* The effect of the number of folds  on the cross_validated  average
performance score.
The K-Nearest neighbor algorithm is used on the vehicles.csv dataset.

* Black formatting applied

* Update vary_folds.py

Co-authored-by: mlopatka <[email protected]>

…fications

 Visualization for misclassifications

* visual for eeg

* code restructured

* #3 data-split space mapped

* fixes issue3

* studied data splits for all classifiers

* added graph in the loop

* docstrings added

* validation sets added

* formatting

* evaluated all classifiers

* compared models

* result added

* calibration plot added

* docstrings

* WIP: created function to plot classification probablities for misclassified data points

* completed first attemp at #63

* minor updates in histogram plots in function plot_misclassified_probablities

* plot correct classes

Fixed #2, train and test a classification model on vehicles dataset

issue#2-trained-model-using-svm-for-vehicles-recognition-using-silhouette

* initial commit

1.
Added notebook for issue # 4
Added helper function issue4_helper.py

* updated code for cross_validation function

* Added function to test cross validation score

* Added new functions and fixed notebook

1. Added fix_outlier_with_boundary_value function
2. Added test_cross_validation function in helpers.py
3. Updated notebook with cross validation test using stratifiedkfold function
4. Updated comments in notebook

* Updated notebook

* Data Loaded from vehicles.csv

* Data visulaization and training model with ifferent algorithms

* Evaluation of model is done.

* Changed model from Logistic Regression to Support Vector Machine

At first attempt i used three differnet models but Logistic Regression , Support Vector Machine and Decision Tree, and the overall accuracy with LR was better than any other but with changing validation parameters in SVM classification , model accuacy increased from 82% to 88%.

* Delete train and test model-checkpoint.ipynb

* Changed file named.

* all python modules were added

* docstrings were added

* labels added in confusion matrix

* Histogram colors were changed into single color

* solved histogram issue

* Update modules.py

* changes made in histogram

* Update modules.py

* sorted histogram

* Update modules.py

* labels were added for confusion matrix

* Python Custom Modules were added

* Update Vehicle_Classifier.ipynb

* Update modules.py

* Update modules.py

* Update modules.py

* added labels in confusion matrix

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Requested Changes were made

* Update modules.py

* change categorical data into numerical data

* change areguments in LR model

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Update modules.py

* Requested changes were made

* Update modules.py

* Update modules.py

* Update modules.py

* Update Vehicle_Classifier.ipynb

* updates file

* Delete Untitled.ipynb

* Update modules.py

* code formatted using python Black

* Requested changes were made

* shifted classifier's code from modules.py to ModelEvaluation.py

* removed learning curves from file

* added function for model evaluation in Model Evaluation file

* updated svm and lr

* added comments

* added doc strings

* Update ModelEvaluation.py

* Update ModelEvaluation.py

* Update Vehicle_Classifier.ipynb

* Update modules.py

* added descriptions

* added interpretations of visualization

* creating another branch from master

* solving branching issues

* main visulaization file is added

* Added module for visualization of missclassification

* added docstring and reformatted to python black

* added interpretation of misclassification

* removed unnecessary comments

Co-authored-by: mlopatka <[email protected]>

* adds a module to visualize misclassification and tests it on winequality.csv

* adds .ipynb and .py for learning from misclassififcations

* Delete visualize_misclass.py

* Delete winequality.ipynb

* Delete winequality_modules.py

…n the train-test split ratio (#72)

* Contribution to issue #2

* Eliminació de l'arxiu de prova

* Eliminació de l'arxiu de prova

* Fixed axes when not numbers and removed superfluous function.

* Minor changes to modules in file data_exploration.py.

Co-authored-by: mlopatka <[email protected]>

* 1. Simple scatter plot
2. Violin and Box plots

* work on previous model

* starting work with prev model

* 1. Added a modeule calibration_plots_module for calibration plots.
2. Added functions for both individual classifier plotting and multiple classifiers plots.

* Fixed axes and elaborated calibration plots

* Added outputs

* Revert "1. Simple scatter plot"

This reverts commit cb26342.

* Python black formatting for modules

* Added titles and labels for axes for plots

* Added relative paths for files

* Minor changes

* Relative path to dataset in repo

* Delete redundant files

* Wine_quality dataset trained

* Recommend feature removed

* recommend feature dropped from the training dataset

* Added additional information in Readme.md for contributors

…om/Sidrah-Madiha/PRESC into Sidrah-Madiha-Comparative_Models_vehicle_dataset

* adds black as pre-commit hook

* adds header info and formats my files

* visualise evaluation metrics

* reformat using black

* removed standard deviation and added min-max band

* added violin plots and examples of exponential and normal distribution

* First attempt on vehicle data with a random forest calssifier

* minor changes

* Comparative model evaluation for vehicle dataset

* first attempt for implementing task 7

* fixes #8

* fixed all change requests

* fixed relative path, improved visualisation

* minor fix in plot

* added absolute distance for comapring with senstivity calculaation

* fixes #8

* fixes #4, attempt 1

* implemeneted all change requests

* formatted code for all helper files

* minor fix

* fixes #5

* fixing conflicts