TO START
# IMPORT DATA LIBRARIES
import pandas as pd
import numpy as np
# IMPORT VIS LIBRARIES
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
# IMPORT MODELLING LIBRARIES
from sklearn.model_selection import train_test_split
# libraries for decision trees
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report,confusion_matrix
# libraries for random forest
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report,confusion_matrix
|
PRELIMINARY OPERATIONS
df = pd.read_csv('data.csv') |
import data |
sns.pairplot(df,hue='col') |
pairplot |
df.info() |
check info df |
df.describe() |
check stats df |
df.head() |
check head df |
TRAIN MODEL - DECISION TREES
SPLIT DATASET |
X = df[['col1','col2',etc.]] |
create df features |
y = df['col'] |
create df var to predict |
X_train, X_test, y_train, y_test =
train_test_split(
X,
y,
test_size=0.3) |
split df in train and test df |
FIT THE MODEL |
tree = DecisionTreeClassifier() |
instatiate model |
tree.fit(X_train, y_train) |
train/fit the model |
MAKE PREDICTIONS |
pred = tree.predict(X_test) |
make predictions |
EVAUATE MODEL |
print(classification_report(y_test,pred)) |
print(confusion_matrix(y_test,pred)) |
|
|
TRAIN MODEL - RANDOM FOREST
SPLIT DATASET |
X = df[['col1','col2',etc.]] |
create df features |
y = df['col'] |
create df var to predict |
X_train, X_test, y_train, y_test =
train_test_split(
X,
y,
test_size=0.3) |
split df in train and test df |
FIT THE MODEL |
rfc = RandomForestClassifier
(n_estimators=200)* |
instatiate model |
rfc.fit(X_train, y_train) |
train/fit the model |
MAKE PREDICTIONS |
rfc_pred = rfc.predict(X_test) |
make predictions |
EVAUATE MODEL |
print(confusion_matrix(y_test,rfc_pred)) |
print(classification_report(y_test,rfc_pred)) |
n_estimators: number of trees to be used in the forest.
|
