synthesized-io · Hilly12 · Aug 26, 2021 · Aug 26, 2021 · Sep 3, 2021 · Sep 3, 2021
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -20,12 +20,6 @@ jobs:
     name: Check Python ${{ matrix.python-version }}
     steps:
     - uses: actions/[email protected]
-      if: ${{ github.event_name == 'pull_request' }}
-      with:
-        ref: ${{ github.head_ref }}
-
-    - uses: actions/[email protected]
-      if: ${{ github.event_name == 'push' }}
 
     - name: Setup Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2

diff --git a/.gitignore b/.gitignore
@@ -6,6 +6,7 @@ build/
 dist/
 *.swp
 src/fairlens/version.py
+src/_version.py
 
 docs/_build/*
 docs/savefig/*

diff --git a/README.md b/README.md
@@ -28,7 +28,7 @@ import pandas as pd
 import fairlens as fl
 
 # Load in the data
-df = pd.read_csv("datasets/compas.csv")
+df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
 
 # Automatically generate a report
 fscorer = fl.FairnessScorer(

diff --git a/datasets/adult.csv b/datasets/adult.csv
diff --git a/datasets/compas.csv b/datasets/compas.csv
diff --git a/datasets/german_credit_data.csv b/datasets/german_credit_data.csv
diff --git a/datasets/titanic.csv b/datasets/titanic.csv
diff --git a/docs/user_guide/adult.nblink b/docs/user_guide/adult.nblink
@@ -0,0 +1,3 @@
+{
+    "path": "../../notebooks/adult.ipynb"
+}
diff --git a/docs/user_guide/correlations.rst b/docs/user_guide/correlations.rst
@@ -84,7 +84,7 @@ the data and check what columns in contains.
 
 .. ipython:: python
 
-    df = pd.read_csv("../datasets/german_credit_data.csv")
+    df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/templates/german_credit_data.csv")
     df
 
 We can generate a correlation heatmap to get a rough idea of any potentially hidden correlations.

diff --git a/docs/user_guide/index.rst b/docs/user_guide/index.rst
@@ -12,6 +12,7 @@ User Guide
   :glob:
   :caption: Tutorials
 
+  adult
   compas
 
 .. toctree::

diff --git a/docs/user_guide/metrics.rst b/docs/user_guide/metrics.rst
@@ -13,7 +13,7 @@ Let's import this method and load in the compas dataset.
   import pandas as pd
   import fairlens as fl
 
-  df = pd.read_csv("../datasets/compas.csv")
+  df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
   df.info()
 
 

diff --git a/docs/user_guide/quickstart.rst b/docs/user_guide/quickstart.rst
@@ -28,7 +28,7 @@ Below we show an assessment of fairness on a subset of Propublica's COMPAS datas
   import pandas as pd
   import fairlens as fl
 
-  df = pd.read_csv("../datasets/compas.csv")
+  df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
   df.info()
 
   fscorer = fl.FairnessScorer(df, "RawScore")

diff --git a/docs/user_guide/scorer.rst b/docs/user_guide/scorer.rst
@@ -29,7 +29,7 @@ and identifying any inherent biases present in a dataset.
   import pandas as pd
   import fairlens as fl
 
-  df = pd.read_csv("../datasets/compas.csv")
+  df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
   df.info()
 
   fscorer = fl.FairnessScorer(df, "RawScore", ["Ethnicity", "Sex"])

diff --git a/docs/user_guide/sensitive.rst b/docs/user_guide/sensitive.rst
@@ -62,7 +62,7 @@ dataset:
 
 .. ipython:: python
 
-    df = pd.read_csv("../datasets/compas.csv")
+    df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
     df.head()
 
     # Apply shallow detection algorithm.
@@ -74,7 +74,7 @@ the sensitive columns to have random names.
 
 .. ipython:: python
 
-    df_deep = pd.read_csv("../datasets/compas.csv")
+    df_deep = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
     df_deep = df_deep.rename(columns={"Ethnicity": "A", "Language": "Random", "MaritalStatus": "B", "Sex": "C"})
 
     # Apply deep detection algorithm.

diff --git a/docs/user_guide/significance.rst b/docs/user_guide/significance.rst
@@ -24,7 +24,7 @@ we can do the following.
   import pandas as pd
   import fairlens as fl
 
-  df = pd.read_csv("../datasets/compas.csv")
+  df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
 
   group1 = df[df["Sex"] == "Male"]["RawScore"]
   group2 = df[df["Sex"] == "Female"]["RawScore"]

diff --git a/docs/user_guide/viz.rst b/docs/user_guide/viz.rst
@@ -17,7 +17,7 @@ First we will import the required packages and load the compas dataset.
 
   fl.plot.use_style()
 
-  df = pd.read_csv("../datasets/compas.csv")
+  df = pd.read_csv("https://raw.githubusercontent.com/synthesized-io/datasets/master/tabular/biased/compas.csv")
   df.info()
-Original file line number
+Diff line change
@@ Expand Up / @@ -12,6 +12,7 @@ User Guide @@
       :glob:
       :caption: Tutorials
+      adult
       compas
     .. toctree::
@@ Expand Down @@