app

app.py

@@ -0,0 +1,9 @@
+import streamlit as st
+from predict_page import show_predict_page
+from explore_page import show_explore_page
+
+new_page=st.sidebar.selectbox("Predict or Explore",("Predict","Explore"))
+if new_page=="Predict":
+    show_predict_page()
+else:
+    show_explore_page()

explore_page.py

@@ -0,0 +1,66 @@
+import streamlit as st
+import pandas as pd 
+import matplotlib.pyplot as plt 
+
+def join_country(cat,cutoff):
+    cat_join={}
+    for i in cat.index:
+        if cat[i]>=cutoff:
+            cat_join[i]=i
+
+        else:
+            cat_join[i]="others"
+    return cat_join
+
+def clean_experience(x):
+    if x=="More than 50 years":
+        return 50
+    if x=="Less than 1 year":
+        return 0.5
+    return float(x)    
+
+def clean_education(x):
+    if "Bachelor’s degree" in x:
+        return "Bachelor’s degree" 
+    if "Master’s degree" in x:
+        return "Master’s degree"
+    if "Professional degree" in x or "Other doctoral" in x:
+            return "Post grad"
+    return "Less than a Bachelors"
+@st.cache
+def load_data():
+    df=pd.read_csv("survey.csv")
+    column_needed=df.loc[:,["Country","EdLevel","YearsCodePro","Employment","ConvertedComp"]]
+    column_needed=column_needed.rename({"ConvertedComp":"Salary"},axis=1)
+    column_needed=column_needed[~column_needed["Salary"].isnull()]
+    column_needed=column_needed.dropna()
+    column_needed= column_needed[column_needed["Employment"]=="Employed full-time"]
+
+    column_needed=column_needed.drop("Employment",axis=1)
+    country_map=join_country(column_needed["Country"].value_counts(),400)
+    column_needed["Country"]=column_needed["Country"].map(country_map)
+    column_needed=column_needed[column_needed["Salary"]<=250000]
+    column_needed=column_needed[column_needed["Salary"]>10000]
+    column_needed=column_needed[column_needed["Country"]!="others"]  
+    column_needed["YearsCodePro"]=column_needed["YearsCodePro"].apply(clean_experience)
+    column_needed["EdLevel"]=column_needed["EdLevel"].apply(clean_education)
+    return column_needed
+data=load_data()
+def show_explore_page():
+    st.title("Explore Software Engineer Average Salary")
+    st.write("""### Stack Overflow Developer Salary""")
+    dataneeded=data["Country"].value_counts()
+    fig,ax=plt.subplots()
+    ax.pie(dataneeded,labels=dataneeded.index,shadow=True,startangle=90)
+    ax.axis("equal")
+    st.write("""#### Number Of Data From Each Country""")
+    st.pyplot(fig)
+
+    st.write("""#### Mean Salary Base On The Country""")
+    mean=data.groupby(["Country"])["Salary"].mean().sort_values(ascending=True)
+    st.bar_chart(mean)
+
+    st.write("""#### Mean Salary Base On The Experience""")
+    mean=data.groupby(["YearsCodePro"])["Salary"].mean().sort_values(ascending=True)
+    st.line_chart(mean)
+    

predict_page.py

@@ -0,0 +1,42 @@
+import streamlit as st
+import pickle
+import numpy as np 
+
+model=pickle.load(open("model.pkl","rb"))
+trans_count=pickle.load(open("trans_count.pkl","rb"))
+trans_edu=pickle.load(open("trans_edu.pkl","rb"))
+print(st.__version__)
+
+def show_predict_page():
+    st.title("Software Developer Salary Prediction")
+    st.write("""## we need some information to predict salary""")
+
+    countries=("United States",
+"India",              
+"United Kingdom",       
+"Germany",               
+"Canada",               
+"Brazil",                
+"France" ,                
+"Spain",                  
+"Australia",              
+"Netherlands",            
+"Poland",               
+"Italy",                  
+"Russian Federation",  
+"Sweden")
+
+    education=("Bachelor’s degree", "Master’s degree", "Post grad","Less than a Bachelors")
+
+    country=st.selectbox("Country" ,countries)
+    education=st.selectbox("Education Level",education)
+    experience=st.slider("Year of EXperience",0,50,3)
+    ok=st.button("Calculate Salary")
+
+    if ok:
+        test=np.array([[country,education,experience]])
+        test[:,0]=trans_count.transform(test[:,0])
+        test[:,1]=trans_edu.transform(test[:,1])
+        test=test.astype(float)
+        salary=model.predict(test)
+        st.subheader(f"The estimated average salary per year is ${salary[0]:.2f}")

requirements.txt

@@ -0,0 +1,4 @@
+matplotlib==3.5.2
+numpy==1.22.3
+pandas==1.4.2
+streamlit==1.9.0