Update app.py

app.py

@@ -1,28 +1,71 @@
 import streamlit as st
 import pandas as pd
 import os
-from scipy.stats import shapiro
+from scipy.stats import shapiro, kstest
+from scipy import stats
 import numpy as np
 import matplotlib.pyplot as plt
+from io import StringIO
 
-col_name = st.text_input('Column to get')
-col_name = str(col_name)
+st.title("Distribution Predictor")
 st.divider()
-upload_file = st.file_uploader("Upload File")
+st.subheader("Select the type of file needed to be Uploaded: ")
+f_format = st.radio(
+    "Select the data format",
+    ['.csv', '.txt'],
+    index=None
+)
 st.divider()
 
-if upload_file is not None:
-    df = pd.read_csv(upload_file)
-    data = np.array(df[col_name])
-    #x = np.arange(0, len(data))
-    fig, ax = plt.subplots()
-    ax.hist(data, bins=100, density=True)
-    stat, p_val = shapiro(data)
+if f_format == '.csv':
+    col_name = st.text_input('Column to get')
+    col_name = str(col_name)
+    st.divider()
+    upload_file = st.file_uploader("Upload File")
+    st.divider()
 
-    if p_val < 0.1:
-        st.write("Data does not follow Normal Distribution")
-    else:
-        st.write("Data does follow Normal Distribution")
+    if upload_file is not None:
+        df = pd.read_csv(upload_file)
+        data = np.array(df[col_name])
+        fig, ax = plt.subplots()
+        ax.hist(data, bins=100, density=True)
+        stat_n, p_val_n = shapiro(data)
+        stat_p, p_val_p = kstest(data, 'poisson', (5, 0))
+        
+        st.divider()
+        if p_val_n > 0.1:
+            st.write("Data follows Normal Distribution")
+        else:
+            st.write("Data does not follow Normal Distribution")
+        
+        st.pyplot(fig)
 
+elif f_format == '.txt':
+    upload_file = st.file_uploader("Upload File")
     st.divider()
-    st.pyplot(fig)
+    if upload_file is not None:
+        stringio = StringIO(upload_file.getvalue().decode("utf-8"))
+        stringio = stringio.getvalue()
+        data = stringio.split(',')
+        data_f = []
+        for i in range(len(data) -1):
+            data_f.append(float(data[i]))
+        fig, ax = plt.subplots()
+        ax.hist(data_f, bins=100, density=True)
+        stat_n, p_val_n = shapiro(data_f)
+        stat_p, p_val_p = kstest(data_f, 'poisson', (5, 0))
+        st.divider()
+        if p_val_n > 0.1:
+            st.write("Data follows Normal Distribution")
+        else:
+            st.write("Data does not follow Normal Distribution")
+        
+        st.pyplot(fig)
+        
+
+
+
+        
+
+    
+