Pinned

1. outlier-detection.ipynb outlier-detection.ipynb

   1

   {

   2

    "cells": [

   3

     {

   4

      "cell_type": "code",

   5

      "execution_count": null,

2. anova_machine.py anova_machine.py

   1

   def anova_machine(Cat_col, target_col, df):

   2

       """ANOVA function.  Provide the target variable column y, the main data set and a categorical column.

   3

       A pivot table will be produced. Then an ANOVA performed to see if the columns are significantly different from each other.   

   4

       Currently set for 95% confidence, will update later for higher significance setting."""

   5

3. outlier_isolation.py outlier_isolation.py

   1

   isolation_forest = IsolationForest(n_estimators=100)

   2

   isolation_forest.fit(df['Sales'].values.reshape(-1, 1))

   3

   xx = np.linspace(df['Sales'].min(), df['Sales'].max(), len(df)).reshape(-1,1)

   4

   anomaly_score = isolation_forest.decision_function(xx)

   5

   outlier = isolation_forest.predict(xx)

4. deterministic-identity-resolution deterministic-identity-resolution Public

   Scala

5. movie-recommendation movie-recommendation Public

   Scala

6. vif_multicollinearity.py vif_multicollinearity.py

   1

   # ------------------------------------------------------------------------------

   2

   # Importing required libraries

   3

   # ------------------------------------------------------------------------------

   4

   from pyspark.sql.types import Row

   5