| import streamlit as st | |
| import numpy as np | |
| import pandas as pd | |
| st.title("***STATISTICS***") | |
| st.caption("*The key to uncover insights of hidden stories in the data*") | |
| st.header("Introduction to statistics") | |
| st.subheader("What is statistics?") | |
| st.write("Statistics is major backbone for the data analysis which is defined as it is a huge feild which majorly deals with the data") | |
| st.write("It majorly collects the data and interprets the data then analyse the collected data and then structrize the analyzed data the whole process is known as statistics") | |
| st.header("Types of statistics") | |
| st.write("Based on the data the statitics are of two types") | |
| st.write("1.Descriptive Statistics/n2.Inferential Statistics") | |
| st.subheader("What is descriptive statistics and its example") | |
| st.write("It describes the collected data and summarizes the data.Descriptive statistics majorly deals with sample data") | |
| st.write("Here the collected data can be sample data or either population data") | |
| st.subheader("What is inferential statistics?") | |
| st.write("Inferential statistics is we want to tell about population data with the help of sample data") | |
| st.subheader("*Sample data*") | |
| st.write("Sample data is subset of population data as we can't collect entire data for every analysis we collect only subpart of entire data") | |
| st.write("Ex: We want to collect the students or members who are taking the data science/ data analysis as domain in India is sample data") | |
| st.subheader("*Population data*") | |
| st.write("Population data is everything together in data is population data.It means the entire data collection without any missing data.") | |
| st.write("Population data is superset and sample data is subset of population data") | |
| st.write("Population data is exact information of data while sample data may have sampling error") | |
| st.write("Ex: We want to collect information about people in the world who are in data science/data analysis domain and who have completed") | |
| st.write("*Measure of sample data is basically known as *Statistics**") | |
| st.write("*Measure of population data is known as *Parameters**") | |
| st.subheader("Types of descriptive statistics") | |
| st.write("Based on the descriptive statistics which are predefined based on measures .They are **1.Measures of central tendency** /n **2.Measures of dispersion(variability)** /n **3.Measures of distribution**") | |
| st.subheader("***Measures of central tendency***") | |
| st.write("It is used to measure the central value or average value of the collected data") | |
| st.write("There are 3 measures in central tendency") | |
| st.subheader("*1.Mean* /n *2.Median* /n *3.Mode*") | |
| st.write("Mode is defined as the data or value which is frequently repeated mostly used for categorical data") | |
| st.write("Median is it gives precise central value of the data used only in ordered data which considers only central values") | |
| st.write("Mean uses all the observations in the data mostly for measuring the central tendency mean is used for exact central value") | |
| st.write("***Mean >> Median >> Mode***") | |
| st.subheader("***Measures of dispersion(variability)***") | |
| st.write("It is used to measure how your collected data is spreaded or dispersed around the cantral value") | |
| st.write("There are 2 measures in dispersion") | |
| st.subheader("*1.Absolute dispersion* /n *2.Relative dispersion*") | |
| st.write("There are four types in absolute dispersion") | |
| st.write("*1.Range* /n *2.Quartile deviation* /n *3.Variance* /n *4.Standard deviation*") | |
| st.write("There are four types in relative dispersion") | |
| st.write("*1.Coefficient of range* /n *2.Coefficient of Quartile deviation* /n *3.Coefficient of Variance* /n *4.Coefficient of Standard deviation*") | |