App and requirements

app.py

@@ -0,0 +1,108 @@
+# -*- coding: utf-8 -*-
+""" Gradio PCOS Prediction .ipynb
+
+Automatically generated by Colaboratory.
+
+The original file is located at
+    https://colab.research.google.com/drive/1W2dPPr1tHmTDgMgZML6C1Ch-4p_tOeZR
+"""
+
+import pandas as pd
+import gradio as gr
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+import sklearn
+from sklearn import tree
+from sklearn.linear_model import LinearRegression
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.preprocessing import scale
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import confusion_matrix
+from sklearn.preprocessing import StandardScaler
+def main(Follicle_No_Right,Follicle_No_Left,Skin_darkening,Hair_growth,Weight_gain,Cycle):
+  url="https://raw.githubusercontent.com/Athulg19/datasets/main/PCOS_clean_data_without_infertility.csv"
+  data = pd.read_csv(url) 
+  data=pd.DataFrame(data)
+  data=data.astype(np.float64)
+  data.dtypes
+  correlation=data.corrwith(data['PCOS (Y/N)']).abs().sort_values(ascending=False)
+  correlation=correlation[correlation>0.4].index
+  data=data[correlation]
+  arr=data.values                     
+  X=arr[:,1:6]                        
+  Y=arr[:,0]
+  scaler=StandardScaler().fit(X)              
+  rescaledX=scaler.transform(X) 
+  np.set_printoptions(precision=3)
+  y=data['PCOS (Y/N)']
+  x=data.drop(['PCOS (Y/N)'],axis=1)
+  X_train,X_test,y_train,y_test = train_test_split(x,y,test_size=.25)
+  logistic = LogisticRegression()
+  logistic.fit(X_train,y_train)
+  data = {'Follicle No. (R)':Follicle_No_Right,'Follicle No. (L)':Follicle_No_Left,'Skin darkening (Y/N)':Skin_darkening,'hair growth(Y/N)':Hair_growth,'Weight gain(Y/N)':Weight_gain,'Cycle(R/I)':Cycle}
+  index = [0]
+  cust_df = pd.DataFrame(data, index)
+  costpredLog = logistic.predict(cust_df)
+  if costpredLog ==0:
+    Prediction = "There is less chance for the patient to catch PCOS"
+  else:
+    Prediction = "There is more chance for the patient to catch PCOS."
+  return  Prediction
+
+iface = gr.Interface(fn = main,
+                     
+inputs =['number','number','number','number','number','number'],
+
+outputs =['text'],
+
+title="Onset of PCOS prediction",
+
+description ='''    Description
+ 
+Polycystic ovary syndrome (PCOS) is a problem with hormones that happens during the reproductive years. If you have PCOS, you may not have periods very often.
+Or you may have periods that last many days. You may also have too much of a hormone called androgen in your body.
+With PCOS, many small sacs of fluid develop along the outer edge of the ovary. These are called cysts. The small fluid-filled cysts contain immature eggs. 
+These are called follicles. The follicles fail to regularly release eggs.
+The exact cause of PCOS is unknown. Early diagnosis and treatment along with weight loss may lower the risk of long-term complications such as type 2 diabetes and heart disease.
+
+    Output0 - Describes the Prediction made
+
+
+More details about the Inputs taken and how they needed to be taken are given below:
+
+          Follicle_No_Right = Number of follicles is in Right Overy 
+          Follicle_No_Left = Number of follicles is in Left Ovary 
+          Skin_darkening = yes(1)/No(0)
+          Hair_growth = yes(1)/No(0)
+          Weight_gain = yes(1)/No(0)
+          Cycle = If it is Regular (0) or Irregular (1)
+         
+         
+''',
+article='''
+Complications of PCOS can include:
+
+          * Infertility
+
+          * Gestational diabetes or pregnancy-induced high blood pressure
+
+          * Miscarriage or premature birth
+
+          * Nonalcoholic steatohepatitis — a severe liver inflammation caused by fat accumulation in the liver
+
+          * Metabolic syndrome — a cluster of conditions including high blood pressure, 
+                            high blood sugar, and abnormal cholesterol or triglyceride levels that significantly increase your risk of cardiovascular disease
+
+          * Type 2 diabetes or prediabetes
+
+          * Sleep apnea
+
+          * Depression, anxiety and eating disorders
+
+          * Abnormal uterine bleeding
+
+          * Cancer of the uterine lining (endometrial cancer)''')
+
+iface.launch(debug =True)

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+numpy
+pandas
+matplotlib
+scikit-learn
+seaborn