update python file

body_performance.py

@@ -7,13 +7,13 @@
 import pandas as pd
 import plotly.express as px
 import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MinMaxScaler
 
-df = pd.read_csv(r'./body_performance.csv')
+df = pd.read_csv(r'.\body_performance.csv')
 
-#print(df.dtypes)
-#df['BMI'] = float(df['weight_kg'])/(float(df['height_cm'])*0.01)^2
 df['BMI'] = df['weight_kg']/(0.0001*df['height_cm']*df['height_cm'])
-df.head()
+print(df.head())
 
 
 # In[ ]:
@@ -29,9 +29,39 @@ df_copy = df.copy()
 # In[ ]:
 
 
+body_train, body_test = train_test_split(df, test_size=int(df["age"].count()*0.2), random_state=1)
+body_test, body_valid = train_test_split(body_test, test_size=int(body_test["age"].count()*0.5), random_state=1)
+
+print("number of elements in data frame: {}".format(df['age'].count()))
+print("train: {}".format(body_train["age"].count()))
+print("test: {}".format(body_test["age"].count()))
+print("valid: {}".format(body_valid["age"].count()))
+
+
+# In[ ]:
+
+
+print(df.describe(include='all'))
+#sit and bend forward_cm jest na minusie!!!
+
+
+# In[ ]:
+
+
+scaler = MinMaxScaler()
+df[['age', 'height_cm', 'weight_kg','body fat_%',
+    'diastolic','systolic','gripForce','sit-ups counts',
+    'broad jump_cm','BMI']] = scaler.fit_transform(df[[
+    'age', 'height_cm', 'weight_kg','body fat_%',
+    'diastolic','systolic','gripForce','sit-ups counts',
+    'broad jump_cm','BMI']])
+
+scaler = MinMaxScaler(feature_range=(-1, 1))
+df['sit and bend forward_cm'] = scaler.fit_transform(df[['sit and bend forward_cm']])
 df.describe(include='all')
 
 
+
 # In[ ]:
 
 
@@ -41,48 +71,70 @@ df.info()
 # In[ ]:
 
 
-df["class"].value_counts().plot(kind="bar")
+print('Each class in data frame: \n{}'.format(df['class'].value_counts()))
+print('Each class in train data: \n{}'.format(body_train['class'].value_counts()))
+print('Each class in test data: \n{}'.format(body_test['class'].value_counts()))
+print('Each class in valid data: \n{}'.format(body_valid['class'].value_counts()))
 
 
 # In[ ]:
 
 
-df[["class","body fat_%"]].groupby("class").mean().plot(kind="bar")
+
 
 
 # In[ ]:
 
 
-sns.set_theme()
 
-sns.relplot(data = df.head(200), x = 'broad jump_cm', y = 'sit-ups counts', hue = 'class')
+
 
 
 # In[ ]:
 
 
-sns.relplot(data = df[df['gender'] == 'M'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')
+#df["class"].value_counts().plot(kind="bar")
 
 
 # In[ ]:
 
 
-sns.relplot(data = df[df['gender'] == 'F'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')
+#df[["class","body fat_%"]].groupby("class").mean().plot(kind="bar")
 
 
 # In[ ]:
 
 
-px.box(df, y=['height_cm',
-              'weight_kg',
-              'body fat_%',
-              'diastolic',
-              'systolic',
-              'gripForce',
-              'sit and bend forward_cm',
-              'sit-ups counts',
-              'broad jump_cm',
-              'BMI'])
+#sns.set_theme()
+
+#sns.relplot(data = df.head(200), x = 'broad jump_cm', y = 'sit-ups counts', hue = 'class')
+
+
+# In[ ]:
+
+
+#sns.relplot(data = df[df['gender'] == 'M'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')
+
+
+# In[ ]:
+
+
+#sns.relplot(data = df[df['gender'] == 'F'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')
+
+
+# In[ ]:
+
+
+#px.box(df, y=['height_cm',
+#               'weight_kg',
+#               'body fat_%',
+#               'diastolic',
+#               'systolic',
+#               'gripForce',
+#               'sit and bend forward_cm',
+#               'sit-ups counts',
+#               'broad jump_cm',
+#               'BMI'])
 
 
 # In[ ]: