Update pages/3_Summary_Statistics.py

pages/3_Summary_Statistics.py

@@ -1,109 +1,109 @@
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-
-import warnings
-warnings.simplefilter(action='ignore', category=UserWarning)
-warnings.simplefilter(action='ignore', category=FutureWarning)
-
-
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-import warnings
-warnings.simplefilter(action='ignore', category=UserWarning)
-warnings.simplefilter(action='ignore', category=FutureWarning)
-
-# Load datasets
-df1 = pd.read_csv('../dataset/ausprivauto0405.csv')
-df2 = pd.read_csv('../dataset/swmotorcycle.csv')
-
-st.title("Summary Statistics")
-
-# ---------------------- DATASET 1 ------------------------
-st.header("Dataset 1: ausprivauto0405")
-
-if st.checkbox("Show raw data (Dataset 1)"):
-    st.subheader("Raw Data")
-    st.write(df1)
-
-if st.checkbox("Show summary statistics (Dataset 1)"):
-    st.subheader('Categorical Variables')
-    obj_cols = df1.select_dtypes(include='object')
-    st.write(obj_cols.describe().T)
-
-    st.subheader('Numerical Variables')
-    num_cols = df1.select_dtypes(exclude='object')
-    st.write(num_cols.describe().T)
-
-st.markdown("""
-## ausprivauto0405 
-is a data frame of 9 columns and 67,856 rows:
-
--Exposure: The number of policy years.
-
--VehValue: The vehicle value in thousand of AUD.
-
--VehAge: The vehicle age group.
-
--VehBody: The vehicle body group.
-
--Gender: The gender of the policyholder.
-
--DrivAge: The age of the policyholder.
-
--ClaimOcc: Indicates occurence of a claim.
-
--ClaimNb: The number of claims.
-
--ClaimAmount: The sum of claim payments. 
-""")
-
-
-# ---------------------- DATASET 2 ------------------------
-st.header("Dataset 2: swmotorcycle")
-
-if st.checkbox("Show raw data (Dataset 2)"):
-    st.subheader("Raw Data")
-    st.write(df2)
-
-if st.checkbox("Show summary statistics (Dataset 2)"):
-    st.subheader('Categorical Variables')
-    obj_cols2 = df2.select_dtypes(include='object')
-    st.write(obj_cols2.describe().T)
-
-    st.subheader('Numerical Variables')
-    num_cols2 = df2.select_dtypes(exclude='object')
-    st.write(num_cols2.describe().T)
-
-
-st.markdown("""
-## swmotorcycle 
-is a data frame of 9 columns and 64,548 rows:
-
--OwnerAge: The owner age.
-
--Gender: The gender.
-
--Area: The type of area.
-
--RiskClass: The motorcycle class, a classification by the so called EV ratio, defined as (Engine
-power in kW x 100) / (Vehicle weight in kg + 75), rounded to the nearest lower integer. The
-75 kg represent the average driver weight. The EV ratios are divided into seven classes.
-
--VehAge: The Vehicle age, between 0 and 99.
-
--BonusClass: The bonusclass, taking values from 1 to 7. A new driver starts with bonus class 1;
-for each claim-free year the bonus class is increased by 1. After the first claim the bonus is
-decreased by 2; the driver can not return to class 7 with less than 6 consecutive claim free
-years.
-
--Exposure: The number of policy years.
-
--ClaimNb: The number of claims.
-
--ClaimAmount: The sum of claim payments.
-""")
-
+import numpy as np
+import pandas as pd
+import streamlit as st
+
+
+import warnings
+warnings.simplefilter(action='ignore', category=UserWarning)
+warnings.simplefilter(action='ignore', category=FutureWarning)
+
+
+import numpy as np
+import pandas as pd
+import streamlit as st
+
+import warnings
+warnings.simplefilter(action='ignore', category=UserWarning)
+warnings.simplefilter(action='ignore', category=FutureWarning)
+
+# Load datasets
+df1 = pd.read_csv('./data/ausprivauto0405.csv')
+df2 = pd.read_csv('./data/swmotorcycle.csv')
+
+st.title("Summary Statistics")
+
+# ---------------------- DATASET 1 ------------------------
+st.header("Dataset 1: ausprivauto0405")
+
+if st.checkbox("Show raw data (Dataset 1)"):
+    st.subheader("Raw Data")
+    st.write(df1)
+
+if st.checkbox("Show summary statistics (Dataset 1)"):
+    st.subheader('Categorical Variables')
+    obj_cols = df1.select_dtypes(include='object')
+    st.write(obj_cols.describe().T)
+
+    st.subheader('Numerical Variables')
+    num_cols = df1.select_dtypes(exclude='object')
+    st.write(num_cols.describe().T)
+
+st.markdown("""
+## ausprivauto0405 
+is a data frame of 9 columns and 67,856 rows:
+
+-Exposure: The number of policy years.
+
+-VehValue: The vehicle value in thousand of AUD.
+
+-VehAge: The vehicle age group.
+
+-VehBody: The vehicle body group.
+
+-Gender: The gender of the policyholder.
+
+-DrivAge: The age of the policyholder.
+
+-ClaimOcc: Indicates occurence of a claim.
+
+-ClaimNb: The number of claims.
+
+-ClaimAmount: The sum of claim payments. 
+""")
+
+
+# ---------------------- DATASET 2 ------------------------
+st.header("Dataset 2: swmotorcycle")
+
+if st.checkbox("Show raw data (Dataset 2)"):
+    st.subheader("Raw Data")
+    st.write(df2)
+
+if st.checkbox("Show summary statistics (Dataset 2)"):
+    st.subheader('Categorical Variables')
+    obj_cols2 = df2.select_dtypes(include='object')
+    st.write(obj_cols2.describe().T)
+
+    st.subheader('Numerical Variables')
+    num_cols2 = df2.select_dtypes(exclude='object')
+    st.write(num_cols2.describe().T)
+
+
+st.markdown("""
+## swmotorcycle 
+is a data frame of 9 columns and 64,548 rows:
+
+-OwnerAge: The owner age.
+
+-Gender: The gender.
+
+-Area: The type of area.
+
+-RiskClass: The motorcycle class, a classification by the so called EV ratio, defined as (Engine
+power in kW x 100) / (Vehicle weight in kg + 75), rounded to the nearest lower integer. The
+75 kg represent the average driver weight. The EV ratios are divided into seven classes.
+
+-VehAge: The Vehicle age, between 0 and 99.
+
+-BonusClass: The bonusclass, taking values from 1 to 7. A new driver starts with bonus class 1;
+for each claim-free year the bonus class is increased by 1. After the first claim the bonus is
+decreased by 2; the driver can not return to class 7 with less than 6 consecutive claim free
+years.
+
+-Exposure: The number of policy years.
+
+-ClaimNb: The number of claims.
+
+-ClaimAmount: The sum of claim payments.
+""")
+