def test_visualize_two_fields(self):
# check if the function works without any error
np.random.seed(1)
df = load_iris(target="species")
df["cat"] = np.random.choice(["a","b","c"],
size=df.shape[0],
replace=True)
inspector = Inspector(df)
## continuous x continuous
inspector.visualize_two_fields("sepal_width","sepal_length")
## continuous x categorical
inspector.visualize_two_fields("sepal_length", "species")
## categorical x continuous
inspector.visualize_two_fields("species", "petal_width")
## categorical x categorical
inspector.visualize_two_fields("species","cat")
# Or there must be a (relatively) clear relation between `workclass` and `label`. Looking at the crosstab of the two fields, we can find that `Never-worked` and `Without-pay` imply "low income". This is obvious, but important to check.
pd.crosstab(df["workclass"], df["label"])
# Anyway, it is very important to see the relation between two fields, because it is part of understanding data.
#
# |feature\target|categorical|continuous|
# |-|-|-|
# |categorical|Bar chart or heatmap|violine|
# |continuous|KDE or histogram|joint plot|
# #### categorical vs categorical
#
# The following bar chart shows the distributions of workclass by label. That is the sum of the (length/area of) blue/red bar is 1.
inspector.visualize_two_fields("workclass", "label")
# We can show the same information by using heatmap. Since we compute the distribution of the `workclass` by `label`, the sum of each row in the heat map is 1.
inspector.visualize_two_fields("workclass", "label", heatmap=True, rotation=10)
# If one or both categorical fields can take lots of values, then it is better to use just a crosstab or its heatmap. A visualization is not always the best solution.
inspector.visualize_two_fields("workclass", "occupation")
inspector.visualize_two_fields("workclass",
"occupation",
heatmap=True,
rotation=10)
# #### categorical vs continuous
# +
np.random.seed(1)
df = load_iris(target="species")
df["cat1"] = np.random.choice(["a", "b", "c"], size=df.shape[0], replace=True)
df["cat2"] = (df.iloc[:, 0] * df.iloc[:, 1] - df.iloc[:, 2] * df.iloc[:, 3] >
11).map({
True: 1,
False: 0
})
inspector = Inspector(df)
inspector ## 4 continuous variables and 3 categorical variables
# -
inspector.visualize_two_fields("sepal_width",
"sepal_length") ## continuous x continuous
inspector.visualize_two_fields("petal_width",
"species") ## continuous x categorical
inspector.visualize_two_fields("species",
"petal_width") ## categorical x continuous
inspector.visualize_two_fields("species", "cat2")
inspector.visualize_two_fields("species", "cat2", heatmap=True)
# +
from sklearn.tree import DecisionTreeClassifier
features = [
"sepal_length", "sepal_width", "petal_length", "petal_width", "cat2"