Upload 5 files

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import requests as req
+from streamlit_lottie import st_lottie
+from prediction_helper import predict_class_way1, predict_class_way2
+
+st.set_page_config(page_title="Welcome to Iris Classifier",page_icon=":blossom:")
+
+with st.container():
+    st.title("Welcome to Iris Classifier :blossom:")
+    st.subheader("Author: Ahmad Baseer")
+    st.write("You can find the code [here](https://github.com/Ahmad-Baseer/AI-Projects)")
+
+st.write("---")
+
+def load_lottieurl(url):
+    r=req.get(url)
+    if r.status_code !=200:
+        None
+    return r.json()
+
+lottie_flower=load_lottieurl("https://lottie.host/db599348-de9d-44a3-9e66-6490a4920520/jiH4zhQwAD.json")
+
+left_col, right_col = st.columns(2)
+
+with left_col:
+    # Create four input fields.
+    sepal_length = st.number_input("Sepal length (cm)", min_value=0.0, max_value=100.0)
+    sepal_width = st.number_input("Sepal width (cm)", min_value=0.0, max_value=100.0)
+    petal_length = st.number_input("Petal length (cm)", min_value=0.0, max_value=100.0)
+    petal_width = st.number_input("Petal width (cm)", min_value=0.0, max_value=100.0)
+
+    datapoint = [sepal_length,sepal_width,petal_length,petal_width]
+
+    # Display the input fields.
+    st.write("Sepal length:", sepal_length)
+    st.write("Sepal width:", sepal_width)
+    st.write("Petal length:", petal_length)
+    st.write("Petal width:", petal_width)
+    st.write(" **This model got accuracy of:** ", 0.8933)
+
+if(sepal_length!=0 and sepal_width!=0 and petal_length!=0 and petal_width!=0):
+    st.write("---")
+    result_1=predict_class_way1(datapoint)
+    result_2=predict_class_way2(datapoint)
+
+    st.write(f" I guess 🤔 it belongs to (using method 1): **{result_1.capitalize()}** ")
+    st.write(f" I guess 🤔 it belongs to (using method 2): **{result_2.capitalize()}** ")
+
+    if result_1==result_2:
+        st.write(" **Hurray :partying_face: we got same results from both techniques!**")
+
+with right_col:
+    st_lottie(lottie_flower,height=250,key="flower")
+
+st.caption("Made with :heart: by Ahmad")
+
+#using local css to design contact form
+def local_css_for_contact_form(file_name):
+    with open(file_name) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+        
+local_css_for_contact_form("style.css")

prediction_helper.py

@@ -0,0 +1,31 @@
+import pickle
+import numpy as np
+from sklearn import datasets
+import pandas as pd
+
+iris_k_mean_model=pickle.load(open('model.sav', 'rb'))
+classes=['versicolor', 'setosa' , 'virginica']
+
+iris = datasets.load_iris()
+x = pd.DataFrame(iris.data, columns=['Sepal Length', 'Sepal Width', 'Petal Length', 'Petal Width'])
+
+
+def predict_class_way1(new_data_point):
+    # Calculate the Euclidean distances between the new data point and each of the training data points.
+    distances = np.linalg.norm(x - new_data_point, axis=1)
+    # print(distances,len(distances),np.argmin(distances))
+
+    # The data point with the minimum Euclidean distance is the class of the new data point.
+    class_label = classes[iris_k_mean_model.labels_[np.argmin(distances)]]
+
+    return class_label
+
+def predict_class_way2(new_data_point):
+    # Calculate the distances between the new data point and each of the cluster centers.
+    distances = np.linalg.norm(iris_k_mean_model.cluster_centers_ - new_data_point, axis=1)
+    # print(distances,len(distances),np.argmin(distances))
+
+    # The data point with the minimum Euclidean distance is the class of the new data point.
+    class_label = classes[np.argmin(distances)]
+
+    return class_label

requirements.txt

@@ -0,0 +1,8 @@
+numpy==1.25.2
+pandas==2.1.0
+Requests==2.25.1
+scikit_learn==1.3.0
+streamlit==1.26.0
+streamlit_lottie==0.0.5
+matplotlib==3.7.3
+seaborn==0.12.2

style.css

@@ -0,0 +1,25 @@
+/* .css-1njjmvq.e1f1d6gn0{
+right: 100px;
+}
+
+.element-container.css-1hynsf2.e1f1d6gn2{
+right: 100px;
+} */
+
+p{
+  font-size: 18px;
+  font-family: 'Times New Roman';
+}
+
+/* Hide Streamlit Branding */
+#MainMenu {
+    visibility: hidden;
+  }
+  
+  footer {
+    visibility: hidden;
+  }
+  
+  header {
+    visibility: hidden;
+  }