betterdatascience

def generate_color(magnitude):
    if magnitude <= 5:
        c_outline, c_fill = '#ffda79', '#ffda79'
        m_opacity, f_opacity = 0.2, 0.1
    else:
        c_outline, c_fill = '#c0392b', '#e74c3c'
        m_opacity, f_opacity = 1, 1
    return c_outline, c_fill, m_opacity, f_opacity

betterdatascience

quake_map = folium.Map(
    location=[-16.495477, 174.9663341],
    zoom_start=5,
    tiles='Stamen Terrain',
    width=1024,
    height=600
)

for _, row in df.iterrows():
    folium.CircleMarker(

betterdatascience

quake_map = folium.Map(
    location=[-16.495477, 174.9663341],
    zoom_start=6,
    tiles='Stamen Terrain',
    width=1024,
    height=600
)

quake_map

betterdatascience

import folium

quake_map = folium.Map(
    location=[-16.495477, 174.9663341],
    zoom_start=6,
    width=1024,
    height=600
)

quake_map

betterdatascience

import pandas as pd

df = pd.read_csv('quakes.csv')
df.head()

betterdatascience

from sklearn.metrics import roc_auc_score, roc_curve

y_test_int = y_test.replace({'Good': 1, 'Bad': 0})
auc_lr = roc_auc_score(y_test_int, probs_lr)
fpr_lr, tpr_lr, thresholds_lr = roc_curve(y_test_int, probs_lr)

auc_dt = roc_auc_score(y_test_int, probs_dt)
fpr_dt, tpr_dt, thresholds_dt = roc_curve(y_test_int, probs_dt)

auc_rf = roc_auc_score(y_test_int, probs_rf)

betterdatascience

from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier

model_lr = LogisticRegression().fit(X_train, y_train)
probs_lr = model_lr.predict_proba(X_test)[:, 1]

model_dt = DecisionTreeClassifier().fit(X_train, y_train)
probs_dt = model_dt.predict_proba(X_test)[:, 1]

betterdatascience

from sklearn.model_selection import train_test_split

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

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42
)

betterdatascience

ax = df['quality'].value_counts().plot(kind='bar', figsize=(10, 6), fontsize=13, color='#087E8B')
ax.set_title('Counts of Bad and Good vines', size=20, pad=30)
ax.set_ylabel('Count', fontsize=14)

for i in ax.patches:
    ax.text(i.get_x() + 0.19, i.get_height() + 100, str(round(i.get_height(), 2)), fontsize=15)

betterdatascience

df['quality'] = ['Good' if quality >= 7 else 'Bad' for quality in df['quality']]