accessnash

# Visualizing time-series

import matplotlib.pyplot as plt

# Plot the aapl time series in blue
plt.plot(aapl, color='blue', label='AAPL')

# Plot the ibm time series in green
plt.plot(ibm, color='green', label='IBM')

accessnash

from sklearn.tree import DecisionTreeClassifier

# Instantiate a DecisionTreeClassifier 'dt' with a maximum depth of 6
dt = DecisionTreeClassifier(max_depth =6, random_state=SEED)

# Fit dt to the training set
dt.fit(X_train, y_train)

# Predict test set labels
y_pred = dt.predict(X_test)

accessnash

from sklearn.model_selection import train_test_split

# Set SEED for reproducibility
SEED = 1

# Split the data into 70% train and 30% test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=SEED)

# Instantiate a DecisionTreeRegressor dt
dt = DecisionTreeRegressor(max_depth=4, min_samples_leaf=0.26, random_state=SEED)

accessnash

from sklearn.tree import DecisionTreeClassifier

# Import BaggingClassifier
from sklearn.ensemble import BaggingClassifier

# Instantiate dt
dt = DecisionTreeClassifier(random_state=1)

# Instantiate bc
bc = BaggingClassifier(base_estimator=dt, n_estimators=50, random_state=1)

accessnash

# Import DecisionTreeClassifier
from sklearn.tree import DecisionTreeClassifier

# Import AdaBoostClassifier
from sklearn.ensemble import AdaBoostClassifier

# Instantiate dt
dt = DecisionTreeClassifier(max_depth=2, random_state=1)

# Instantiate ada

accessnash

# Define params_dt
params_dt = {
'max_depth': [2, 3, 4],
'min_samples_leaf': [0.12, 0.14, 0.16, 0.18],
}

# Import GridSearchCV
from sklearn.model_selection import GridSearchCV

# Instantiate grid_dt

accessnash

print(basetable.head())
# Assign the number of rows in the basetable to the variable 'population_size'.
population_size  = len(basetable)
# Print the population size.
print(population_size)
# Assign the number of targets to the variable 'targets_count'.
targets_count = sum(basetable["target"])
# Print the number of targets.
print(targets_count)
# Print the incidence, i.e. the number of targets divided by the population size.

accessnash

# Import the linear_model and roc_auc_score modules
from sklearn import linear_model
from sklearn.metrics import roc_auc_score

# Consider two sets of variables
variables_1 = ["mean_gift","income_low"]
variables_2 = ["mean_gift","income_low","gender_F","country_India","age"]

# Make predictions using the first set of variables and assign the AUC to auc_1
X_1 = basetable[variables_1]

accessnash

# Cumulative Gains curve

import matplotlib.pyplot as plt

# Import the scikitplot module
import scikitplot as skplt

# Plot the cumulative gains graph
skplt.metrics.plot_cumulative_gain(targets_test, predictions_test)
plt.show()

accessnash

# Predictor inside graph

# Inspect the predictor insight graph table of Country
print(pig_table)

# Print the number of UK donors
print(pig_table["Size"][pig_table["Country"]=="UK"])

# Check the target incidence of USA and India donors
print(pig_table["Incidence"][pig_table["Country"]=="USA"])