loss_function='Logloss',
verbose=True)
# train the model
model.fit(train_data, train_labels)
# make the prediction using the resulting model
preds_class = model.predict(test_data)
preds_proba = model.predict_proba(test_data)
print("class = ", preds_class)
print("proba = ", preds_proba)
return preds_class, preds_proba
if __name__ == "__main__":
df_train = clean(
pd.read_csv(
'/Users/jacobtryba/DSI/assignments/supervised-learning-case-study/data/churn_train.csv'
)).drop('months_as_user', axis=1)
df_test = clean(
pd.read_csv(
'/Users/jacobtryba/DSI/assignments/supervised-learning-case-study/data/churn_test.csv'
)).drop('months_as_user', axis=1)
X_train, X_test, y_train, y_test = X_y(df_train)
model = CatBoostClassifier(iterations=2,
depth=2,
learning_rate=1,
loss_function='Logloss',
verbose=True)
# train the model
model.fit(X_train, y_train)
from catboost import CatBoostClassifier, Pool
from sklearn.metrics import confusion_matrix
from sklearn.metrics import mean_squared_error, accuracy_score
from sklearn.ensemble import GradientBoostingClassifier as GBC
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
plt.style.use('fivethirtyeight')
if __name__ == "__main__":
### Get Data ###
df_train = clean(pd.read_csv('../data/churn_train.csv')).drop(
['avg_rating_by_driver', "city"], axis=1)
df_test = clean(pd.read_csv('../data/churn_test.csv')).drop(
['avg_rating_by_driver', "city"], axis=1)
X, y = X_y(df_train)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
X_cols = [
'avg_dist', 'avg_rating_of_driver', 'avg_surge', 'phone', 'surge_pct',
'trips_in_first_30_days', 'luxury_car_user', 'weekday_pct'
]
### Random Forest ###
rf = RandomForestClassifier(n_estimators=200, max_depth=8)
rf.fit(X_train, y_train)
from catboost import CatBoostClassifier, Pool
from sklearn.metrics import confusion_matrix
from sklearn.metrics import mean_squared_error, accuracy_score
from sklearn.ensemble import GradientBoostingClassifier as GBC
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
plt.style.use('fivethirtyeight')
if __name__ == "__main__":
### Get Data ###
df_train = clean(pd.read_csv('../data/churn_train.csv'))
df_test = clean(pd.read_csv('../data/churn_test.csv'))
X, y = X_y(df_train)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
X_cols = [
'avg_dist', 'avg_rating_by_driver', 'avg_rating_of_driver',
'avg_surge', 'phone', 'surge_pct', 'trips_in_first_30_days',
'luxury_car_user', 'weekday_pct', 'is_Astapor', "is_King's Landing"
]
### Random Forest ###
rf = RandomForestClassifier(n_estimators=200, max_depth=8)
rf.fit(X_train, y_train)
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sys
import seaborn as sns
sys.path.append(
'/home/mike/dsi/case_studies/supervised-learning-case-study/src/')
from clean_df import clean, X_y
from sklearn.linear_model import LogisticRegressionCV
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
if __name__ == '__main__':
df_train = clean(pd.read_csv('../data/churn_train.csv')).drop(
'months_as_user', axis=1)
df_test = clean(pd.read_csv('../data/churn_test.csv')).drop(
'months_as_user', axis=1)
X_train, X_test, y_train, y_test = X_y(df_train)
log_model = LogisticRegression(class_weight='balanced')
log_model.fit(X_train, y_train)
y_pred_p = log_model.predict_proba(X_test)
y_pred = log_model.predict(X_test)
score_train = log_model.score(X_train, y_train)
score_test = log_model.score(X_test, y_test)
# ## Validation