SurajDataScientist/Exploratory_Data_Analysis_using_python_Libraries

1import streamlit as st2import pandas as pd3import numpy as np 4 5st.title("Pandas")6 7page = st.sidebar.radio("Choose topic", [8    "Introduction", 9    "Series", 10    "Data frame", 11    "read_csv", 12    "read_excel"13])14 15 16if page == "Introduction":17    st.title("Introduction")18 19 20    st.write("Pandas is one of the most important and widely used library of the python for data analysis, it is mainly used for data manipulation and exploratory data analysis.")21    st.image("https://miro.medium.com/v2/resize:fit:1080/1*xRcXl9YKgpnb0zvXLvZprg.jpeg", width = 305)22 23    st.write("In pandas we mainly work with datastructures (Series and DataFrames) and Tools which are used for Data analysis, Data cleaning and Data structuring")24 25    st.image("https://www.altexsoft.com/static/blog-post/2024/5/36514c36-b2f0-48a2-8072-c915c5f98dd5.webp",width = 700)26    27    st.write("Here it works with two kinds of data structures called series and Dataframe.")28    st.write("Series is a 1-dimensional labelled array and Data frame is a 2-dimensional labelled array, here what is common in these 2 datastructures are they are both labelled which makes the data more easier to identify and use it for analysis.")29    st.image("https://www.altexsoft.com/static/blog-post/2024/2/a2b6d6bd-898e-424f-98a8-50b3bdf775eb.png",width=600)30 31 32 33 34elif page == "Series":    35    st.header("Series")36    st.write("Series is a 1-dimensional labelled array. We should always imagine series as a single column vector.")37    st.markdown("""38    **Properties of Series:**39    1. It contains only **homogeneous** data  40    2. It is **mutable**  41    3. It is a **sequential** data type42    """)43 44    st.write("**Creating a series**")45 46 47    st.write("This will return you an empty series object.")48    with st.echo():49        import pandas as pd50        var1 = pd.Series([])51    st.code(var1, language="python")52 53 54    st.write("This will create basic simple series")55    with st.echo():56        var2 = pd.Series([1,2,3,4])57    st.code(var2, language='python')58 59 60    st.write(" Giving labels(which are customizable) index names to the values.")61    with st.echo():62        var3 = pd.Series([1,2,3,4],dtype=np.int8,index=['a','b','c','d'])63    st.code(var3, language='python')64 65 66    st.write("**Series attributes**")67    with st.echo():68        var2.ndim69        #to know the dimension of the series- It will always return 1.70        71    with st.echo():72        var2.shape73        # to know the shape of the series74    75    with st.echo(): 76        var2.size77        #to know the size of series78    79    with st.echo(): 80        c1 = var2.values81        # to convert series into an array82    st.code(c1, language='python')83    with st.echo():84        var2.dtype85         # to know the data type of series elements86    87 88 89    st.write("**Series methods**")90    with st.echo():91        d1 = pd.Series(range(100,400))92    st.code(d1, language='python')93 94    st.write(" head() - by default it will return the first 5 elemnts, to cutsomize number we should give number in parameter.")95    with st.echo():96        d1.head()97    st.code(d1.head(), language='python') 98 99    st.write("tail() - tail will return last 5 elements,by default it will return the last 5 elemnts,  to cutsomize number we should give number in parameter.")100    with st.echo():101        d1.tail()102    st.code(d1.tail(), language='python')103 104 105    st.write("astype()- astype method will help us to return modify the data type of the series.")106    with st.echo():107        d1.astype(np.int16)108    st.code(d1.astype(np.int16), language='python')109 110    st.write("memory_usage() - It is used to check the how much memory is being utilized by the series.")111    with st.echo():112        d1.memory_usage()113    st.code(d1.memory_usage(), language='python')114 115 116    st.write("drop() - it is used to drop the certain values from series and here drop is done by accessing index of the series and mentioning index inside drop function parameter.")117    st.write("Let's look at this series d1 and compare after applying drop() method.")118    st.code(d1, language='python')119    with st.echo():         120        d1.drop(labels=[2,4,6])121    st.code(d1.drop(labels=[2,4,6]), language='python')122 123 124    st.write("**Accessing the elements**")125    st.write("We can access the elements inside a series using loc[] and iloc[].")126    st.write("loc[]- loc is used while accessing elements by labels which are given by user/tempoarary labels.")127    st.write("iloc[] - iloc is used to access elements by permanent label/default label given by system.")128 129 130    with st.echo():131        data = pd.Series(range(10,15),index=["a","b","c","d","e"])132    st.code(data, language='python')133 134    st.write("iloc - can be used in 3 ways - 1.single element accessing, 2.Integer accessing, 3.Slicing")135    with st.echo():136        y1 = data.iloc[0]137    138    st.code(y1, language='python')139    with st.echo():140        y2 = data.iloc[[0,3,2,4]]141    142    st.code(y2, language='python')  143 144    with st.echo():145        y3 = data.iloc[1:4]146        147    st.code(y3, language='python') 148 149 150    st.write("loc - can also be used in 3 ways - 1.single element accessing, 2.Integer accessing, 3.Slicing")151    with st.echo():152        z1 = data.loc["a"]153    st.code(z1, language='python')154 155    with st.echo():156        z2 = data.loc[["a","d","c","b"]]157    158    st.code(z2, language='python')  159 160    with st.echo():161        z3 = data.loc["a":"d"]162    st.code(z3, language='python')163        164        165