diabetes dataset link

 data set diabetes


https://classroom.google.com/c/NjE3OTk5MTQ1Mzkz/m/NjQ0MzYyODM4MzMx/details

Comments

Post a Comment

Popular posts from this blog

Pima Dataset

  #import pandas library import pandas as pd from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier from sklearn.model_selection import train_test_split # Import train_test_split function from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation col_names = [ 'pregnant' , 'glucose' , 'bp' , 'skin' , 'insulin' , 'bmi' , 'pedigree' , 'age' , 'label' ] pima = pd.read_csv( "diabetes.csv" , header = None , names = col_names) feature_cols = [ 'pregnant' , 'insulin' , 'bmi' , 'age' , 'glucose' , 'bp' , 'pedigree' ] x = pima[feature_cols] y = pima.label x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3 , random_state = 1 ) # Create Decision Tree classifer object clf = DecisionTreeClassifier( criterion = 'entropy' , max_depth = 3 ) # Train Decisi...
Read more

Diabetes pandas(Python)

 import pandas as pd # Read the dataset df = pd.read_csv('pima-indians-diabetes.csv') # Set column names df.columns = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'] # Identify and remove duplicate consecutive rows with the same class df = df.drop_duplicates(subset='class', keep='first') # Calculate the averages of the features averages = df.groupby('class').mean().reset_index() # Calculate the percentage reduction original_rows = len(df) reduced_rows = len(averages) percentage_reduction = ((original_rows - reduced_rows) / original_rows) * 100 # Print the new dataframe print(averages) print(f"Percentage reduction: {percentage_reduction:.2f}%")
Read more

Python Wheather Lab Work

  import pandas as pd  weather_data= {      'day':['4/05/2022', '4/04 /2023', '10/02/2011', '30/09/2021', '9/10/2001','13/05/2019'],     'temp':['20','30','45','39','25','51'],     'windspeed':['7','3','5','9'],      'event':['rain', 'sunny', 'Litt cloudy', 'cloudy', 'sunny', 'windy'],     } df= pd.DataFrame(weather_data) rows, columns= df.shape df.tail(2)  df[2:5] df.columns  df['day']  df[['day' 'event']]  df['temp'].max()  df['temp'].mean()  df['temp'].min()  df['temp'].std()  df.describe()  df['temp']=df['temp'].astype(int)  df[df['temp']>32] df[df.tempdf.temp.max()]  df[['day', 'temp']][df.tempdf.temp.max()]  #df-index()  df.set_index("day", inplace=True)  df.loc['4...
Read more