r0r-5chach
/
barclays_challenge_event_2024_backend
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

init routes

This commit is contained in:
Joshua Perry 2024-04-04 03:47:57 +01:00
parent 2371f14c3c
commit 2b553d78e3
15 changed files with 165 additions and 161 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -2,4 +2,3 @@ __pycache__
build
barclays_credit_classifier.egg-info
.env

0
db.py Normal file
View File

17
docker/docker-compose.yml Normal file
View File

@ -0,0 +1,17 @@
services:
mongo:
image: mongo
restart: always
environment:
MONGO_INITDB_ROOT_USERNAME: root
MONGO_INITDB_ROOT_PASSWORD: example
ports:
- 27017:27017
server:
build:
context: .
dockerfile: server.Dockerfile
ports:
- 12345:12345

11
docker/server.Dockerfile Normal file
View File

@ -0,0 +1,11 @@
FROM python:3
WORKDIR $HOME/projects/uni/barclays_challenge_event_2024/
ADD setup.py ./
ADD routes/ ./
ADD model/ ./
ADD main.py ./
ADD db.py ./
ADD credit_risk_dataset.csv ./
RUN pip install .

77
main.py
View File

@ -1,77 +0,0 @@
import models
import pandas as pd
import preprocessing as pp
from sklearn.metrics import accuracy_score
# Load Data
credit_risk = pd.read_csv("credit_risk_dataset.csv")
# Feature Addition
# Feature Conversion
person_home_ownership_values = {
"RENT": 1,
"MORTGAGE": 2,
"OWN": 3,
"OTHER": 4,
}
loan_intent_values = {
"EDUCATIONAL": 1,
"MEDICAL": 2,
"VENTURE": 3,
"PERSONAL": 4,
"DEBTCONSOLIDATION": 5
}
loan_grade_values = {
"A": 1,
"B": 2,
"C": 3,
"D": 4,
"E": 5
}
cb_person_default_on_file_values = {
"Y": 1,
"N": 0,
}
# Convert categorical column to a numerical column
credit_risk["person_home_ownership"] = credit_risk["person_home_ownership"].map(person_home_ownership_values)
credit_risk["loan_intent"] = credit_risk["loan_intent"].map(loan_intent_values)
credit_risk["loan_grade"] = credit_risk["loan_grade"].map(loan_grade_values)
credit_risk["cb_person_default_on_file"] = credit_risk["cb_person_default_on_file"].map(cb_person_default_on_file_values)
print("Feature Conversion Complete")
# Feature Removal
# columns_for_removal = ["housing_median_age", "total_rooms", "total_bedrooms"]
# for column in columns_for_removal:
# housing.drop(column, axis=1, inplace=True)
# Preprocessing
credit_risk = pp.impute_missing_values(credit_risk) # Handle missing values
print("Missing Values handling Complete")
# housing = pp.remove_outliers(housing) #Remove outliers
# Training and Testing Preperation
training_features, training_target_value, test_features, test_target_value = pp.training_test_split(credit_risk, "loan_status") # Split the data into Training and Test sets
print("Training and Test features split Complete")
# Normalise the data
training_features, test_features = pp.normalise(training_features,
test_features)
print("Normalisation Complete")
# Init Models
rf_model = models.random_forest_classifier(training_features,
training_target_value)
print("Model Init Complete")
# Get Predictions
rf_predictions = rf_model.predict(test_features)
print("Predictions Complete")
# Compare Results
accuracy = accuracy_score(test_target_value, rf_predictions)
print(f"Accuracy: {accuracy}")
print(rf_predictions)

69
model/model.py Normal file
View File

@ -0,0 +1,69 @@
import pandas as pd
import preprocessing as pp
from sklearn.ensemble import RandomForestClassifier
# Feature Conversion Values
categorical_columns = ["person_home_ownership",
"loan_intent",
"loan_grade",
"cb_person_default_on_file"]
person_home_ownership_values = {
"RENT": 1,
"MORTGAGE": 2,
"OWN": 3,
"OTHER": 4,
}
loan_intent_values = {
"EDUCATIONAL": 1,
"MEDICAL": 2,
"VENTURE": 3,
"PERSONAL": 4,
"DEBTCONSOLIDATION": 5
}
loan_grade_values = {
"A": 1,
"B": 2,
"C": 3,
"D": 4,
"E": 5
}
cb_person_default_on_file_values = {
"Y": 1,
"N": 0,
}
def get_default_predictor():
data = pd.from_csv("credit_risk_dataset.csv")
data = convert_categories(data)
# Imputation
data = pp.impute_missing_values(data)
# Training and Testing Preperation
train_features, train_target, test_features, test_target = pp.training_test_split(data, "loan_status")
# Normalise the data
training_features, test_features = pp.normalise(train_features,
test_features)
# Init Models
rf_model = random_forest_classifier(training_features,
train_target)
return rf_model
def random_forest_classifier(training_features, training_target):
model = RandomForestClassifier(max_features="log2",
random_state=79,
n_jobs=-1)
return model
def convert_categories(data):
data["person_home_ownership"] = data["person_home_ownership"].map(
person_home_ownership_values)
data["loan_intent"] = data["loan_intent"].map(loan_intent_values)
data["loan_grade"] = data["loan_grade"].map(loan_grade_values)
data["cb_person_default_on_file"] = data["cb_person_default_on_file"].map(
cb_person_default_on_file_values)
return data

0
preprocessing.py → model/preprocessing.py
View File

9
models.py
View File

@ -1,9 +0,0 @@
from sklearn.ensemble import RandomForestClassifier
def random_forest_classifier(training_features, training_target):
model = RandomForestClassifier(max_features="log2",
random_state=79,
n_jobs=-1)
model.fit(training_features, training_target)
return model

11
routes/application_routes.py Normal file
View File

@ -0,0 +1,11 @@
from flask import Blueprint
blueprint = Blueprint("user", __name__)
@blueprint.route("/api/user", methods=["POST"])
@blueprint.route("/api/user", methods=["PATCH"])
@blueprint.route("/api/user", methods=["GET"])
@blueprint.route("/api/user", methods=["OPTIONS"])

15
routes/authentication_routes.py Normal file
View File

@ -0,0 +1,15 @@
from flask import Blueprint, request
blueprint = Blueprint("application", __name__)
@blueprint.route("/api/application/apply", methods=["POST"])
def process_application():
req = request.json
@blueprint.route("/api/application", methods=["PATCH"])
@blueprint.route("/api/application", methods=["OPTIONS"])
@blueprint.route("/api/application", methods=["GET"])
def authenticate_user():
req = request.json

7
routes/bureau_routes.py Normal file
View File

@ -0,0 +1,7 @@
from flask import Blueprint
blueprint = Blueprint("user", __name__)
@blueprint.route("/api/user", methods=["GET"])
@blueprint.route("/api/user", methods=["OPTIONS"])

13
routes/referral_routes.py Normal file
View File

@ -0,0 +1,13 @@
from flask import Blueprint
blueprint = Blueprint("user", __name__)
@blueprint.route("/api/referral", methods=["POST"])
@blueprint.route("/api/referral", methods=["PATCH"])
@blueprint.route("/api/referral", methods=["DELETE"])
@blueprint.route("/api/referral", methods=["GET"])
@blueprint.route("/api/referral", methods=["OPTIONS"])

15
routes/user_routes.py Normal file
View File

@ -0,0 +1,15 @@
from flask import Blueprint
blueprint = Blueprint("user", __name__)
@blueprint.route("/api/user", methods=["POST"])
@blueprint.route("/api/user", methods=["PUT"])
@blueprint.route("/api/user", methods=["PATCH"])
@blueprint.route("/api/user", methods=["DELETE"])
@blueprint.route("/api/user", methods=["GET"])
@blueprint.route("/api/user", methods=["OPTIONS"])

15
setup.py
View File

@ -1,18 +1,17 @@
from setuptools import setup, find_packages
setup(
name="barclays_credit_classifier",
name="Credit Assessment",
version="1.0.0",
description="Predicts whether someone will default on their loan. Uses the Credit Risk Dataset from Kaggle",
author="r0r-5chach",
description="ML Assisted Credit Assessment",
author="r0r-5chach",
author_email="r0r-5chach.xyz@proton.me",
packages=find_packages(),
install_requires=[
"numpy",
"scipy",
"matplotlib",
"pandas",
"asyncio",
"Flask",
"scikit-learn",
"seaborn"
"pandas",
"pymongo"
]
)

66
visualisations.py
View File

@ -1,66 +0,0 @@
import matplotlib.pyplot as plt
import seaborn as sns
def missing_value_pairwise_plots(data_frame, null_column, save=False):
not_missing_data = data_frame.dropna()
mising_data = data_frame[data_frame[null_column].isnull()]
for column in data_frame.columns:
if column != null_column:
plt.figure()
plt.title(f"Scatter Plot of {column} against {null_column}")
plot_missing_values(column)
plt.scatter(not_missing_data[column], not_missing_data[null_column], color=[[0.502, 0, 0.502, 0.4]], label="Existing Values")
plt.xlabel(column)
plt.ylabel(null_column)
plt.legend()
if save:
plt.savefig(f"missing_values[{column}:{null_column}].png")
else:
plt.show()
plt.close()
def plot_missing_values(column):
plt.plot([], [], color="red", alpha=0.4, label="Missing Values")
for value in column:
plt.axvline(x=value, color="red", alpha=0.4)
def correlation_matrix(data_frame, save=False):
matrix = data_frame.corr()
plt.figure()
sns.heatmap(matrix, annot=True)
plt.title("Correlation Matrix of Existing Features")
if save:
plt.savefig("correlation_matrix.png")
else:
plt.show()
plt.close()
def imputation_plots(data_frame, imputed_data, null_column, columns, save=False):
not_missing_data = data_frame.dropna()
for column in columns:
plt.figure()
plt.scatter(imputed_data[column], imputed_data[null_column], color=[[0, 0.502, 0, 0.4]], label="Imputed Data")
plt.scatter(not_missing_data[column], not_missing_data[null_column], colot=[[0.502, 0, 0.502, 0,4]], label="Original Data")
plt.title(f"Scatter Plot of {column} against {null_column} after KNN(9) Imputation")
plt.xlabel(column)
plt.ylabel(column)
plt.legend()
if save:
plt.savefig(f"imputation_results[{column}:{null_column}].png")
else:
plt.show()
plt.close()
def outlier_box_plots(data_frame, save=False):
for column in data_frame.columns:
plt.figure()
plt.title(f"Box Plot of {column}")
plt.boxplot(data_frame[column])
plt.ylabel(column)
plt.xticks(rotation=45)
if save:
plt.savefig(f"outlier_box_plot[{column}].png")
else:
plt.show()
plt.close()