app.py

app.py

@@ -0,0 +1,83 @@
+import pandas as pd
+import numpy as np
+import seaborn as sn
+import matplotlib.pyplot as plt
+import plotly.express as px
+
+df=pd.read_csv('Placement_Data_Full_Class.csv')
+
+df.drop(columns=['sl_no'],axis=1,inplace=True)
+
+df_encoded=pd.get_dummies(df,columns=['gender','ssc_b',"hsc_b","workex","hsc_s","degree_t","specialisation","status"],prefix=['gender','ssc_b',"hsc_b","workex","hsc_s","degree_t","specialisation","status"], drop_first=True)
+
+df_encoded.drop(columns='salary',axis=1,inplace=True)
+
+test=df_encoded['status_Placed']
+train=df_encoded.drop(columns='status_Placed',axis=1)
+
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.svm import SVC
+from sklearn import tree
+from sklearn.model_selection import train_test_split
+from sklearn import metrics
+
+x_train,x_test,y_train,y_test=train_test_split(train,test,test_size=0.2,random_state=0)
+
+from sklearn.preprocessing import StandardScaler
+ss=StandardScaler()
+x_train=ss.fit_transform(x_train)
+x_test=ss.transform(x_test)
+
+lr = LogisticRegression()
+
+lr.fit(x_train,y_train)
+#y_pred = lr.predict(x_test)
+#print(metrics.accuracy_score(y_test,y_pred))
+
+# Define the prediction function
+def predict_placement_status(ssc_p,hsc_p,degree_p,etest_p,mba_p,gender_M,ssc_b_Others,hsc_b_Others,workex_Yes,hsc_s_Commerce,hsc_s_Science,degree_t_Others,degree_t_Sci_Tech,specialisation_Mkt_HR):
+
+  gender_M = 1 if gender_M == "Male" else 0
+  ssc_b_Others = 1 if ssc_b_Others == "Others" else 0
+  hsc_b_Others = 1 if hsc_b_Others == "Others" else 0
+  workex_Yes = 1 if workex_Yes == "Yes" else 0
+  hsc_s_Commerce = 1 if hsc_s_Commerce == "Commerce" else 0
+  hsc_s_Science = 1 if hsc_s_Science == "Science" else 0
+  degree_t_Others = 1 if degree_t_Others == "Others" else 0
+  degree_t_Sci_Tech = 1 if degree_t_Sci_Tech == "Sci&Tech" else 0
+  specialisation_Mkt_HR = 1 if specialisation_Mkt_HR == "Mkt&HR" else 0
+  input_data = [[float(ssc_p),float(hsc_p),float(degree_p),float(etest_p),float(mba_p),gender_M,ssc_b_Others,hsc_b_Others,workex_Yes,hsc_s_Commerce,hsc_s_Science,degree_t_Others,degree_t_Sci_Tech,specialisation_Mkt_HR]]
+
+
+
+  input_data_scaled = ss.transform(input_data)
+  prediction = lr.predict(input_data_scaled)
+  return "Placed" if prediction[0] == 1 else "Not Placed"
+
+
+
+iface = gr.Interface(fn=predict_placement_status,
+                     inputs=[gr.Number(label="SSC Marks"),
+                             gr.Number(label="HSC Marks"),
+                             gr.Number(label="Degree Marks"),
+                             gr.Number(label="Emploibility-test Marks"),
+                             gr.Number(label="MBA Marks"),
+                             gr.Radio(label="Gender", choices=["Female", "Male"]),
+                             gr.Radio(label="SSC Board", choices=["Central", "Others"]),
+                             gr.Radio(label="HSC Board", choices=["Central", "Others"]),
+                             gr.Radio(label="Work Experience", choices=["No", "Yes"]),
+                             gr.Radio(label="HSC Stream", choices=["Commerce", "Science", "Arts"]),
+                             gr.Radio(label="HSC Stream", choices=["Commerce", "Science", "Arts"]),
+                             gr.Radio(label="Degree Type", choices=["Others", "Sci&Tech", "Comm&Mgmt"]),
+                             gr.Radio(label="Degree Type", choices=["Others", "Sci&Tech", "Comm&Mgmt"]),
+                             gr.Radio(label="Specialisation", choices=["Mkt&HR", "Mkt&Fin"]),
+                     ],
+                     outputs="text",
+                     title="Prediction",
+                     description="Predict based on selected features.",theme='compact'
+                  )
+
+iface.launch(share=True)
+