abhisheknigam / expedia-hotel-recommendation Goto Github PK

Execution Steps for decision tree algo:
1. Download and extract the train dataset. It will be extracted as train.csv
2. Run python expedia_decision_tree.py to run the algorithm
3. If you have to run on a dataset with smaller rows. Please changed line #164 to reflect the proper file name and run the algorithm using command given in 2.

Execution steps for SVM Algorithm

1. Download and extract the train dataset.
2. Move inside the directory where you downloaded "train.csv"
3. run python Multiclass-Svm.py

Execution steps for Softmax Algorithm

1. Download and extract the train dataset.
2. Move inside the directory where you downloaded "train.csv"
3. run python Softmax.py

Execution steps for Random Forest Algorithm
1. Download and extract the train dataset.
2. Move inside the directory where you downloaded "train.csv"
3. run python Random_forest_algorithm.py
4. Currently it is running for 5 clusters, if you need to run for 2 or entire clusters, comment code line # 290.


Execution steps for Naive Bayes Algorithm

1. Download and extract the train dataset.
2. Move inside the directory where you downloaded "train.csv"
3. Open the Ipython notebook - Naive Bayes Implementation.ipynb in Anaconda or use the NaiveBayes.py file to run the code. Ipthon notebook is preferred as the code was developed on it.
4. Run all the cells.