betterdatascience

plt.figure()

joyplot(
    data=sydney[['MaxTemp', 'Month']], 
    by='Month',
    figsize=(12, 8)
)
plt.title('Ridgeline Plot of Max Temperatures in Sydney', fontsize=20)
plt.show()

betterdatascience

from pandas.api.types import CategoricalDtype

cat_month = CategoricalDtype(
    ['January', 'February', 'March', 'April', 'May', 'June',
     'July', 'August', 'September', 'October', 'November', 'December']
)

sydney['Month'] = sydney['Month'].astype(cat_month)

sydney.dtypes

betterdatascience

sydney = df.query("Location == 'Sydney'")
sydney = sydney.drop('Location', axis=1)
sydney['Date'] = sydney['Date'].astype('datetime64')
sydney['Month'] = sydney['Date'].dt.month_name()

sydney.head()

betterdatascience

import pandas as pd
import matplotlib.pyplot as plt
from joypy import joyplot

df = pd.read_csv('weatherAUS.csv', usecols=['Date', 'Location', 'MinTemp', 'MaxTemp'])
df.head()

betterdatascience

exp = explainer.explain_instance(
    data_row=X_test.iloc[4], 
    predict_fn=model.predict_proba
)

exp.show_in_notebook(show_table=True)

betterdatascience

exp = explainer.explain_instance(
    data_row=X_test.iloc[1], 
    predict_fn=model.predict_proba
)

exp.show_in_notebook(show_table=True)

betterdatascience

import lime
from lime import lime_tabular

explainer = lime_tabular.LimeTabularExplainer(
    training_data=np.array(X_train),
    feature_names=X_train.columns,
    class_names=['bad', 'good'],
    mode='classification'
)

betterdatascience

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)
score = model.score(X_test, y_test)

betterdatascience

from sklearn.model_selection import train_test_split

X = wine.drop('quality', axis=1)
y = wine['quality']

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

betterdatascience

import numpy as np
import pandas as pd

wine = pd.read_csv('wine.csv')
wine.head()