Upload 21 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pages/matt.jpg filter=lfs diff=lfs merge=lfs -text
+pages/parot.jpg filter=lfs diff=lfs merge=lfs -text
+raw2.gif filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,92 @@
+import joblib
+import streamlit as st
+from sklearn.ensemble import RandomForestRegressor
+import base64
+
+
+# Using "with" notation
+st.markdown(
+    f'''
+        <style>
+            .sidebar .sidebar-content {{
+                width: 375px;
+            }}
+        </style>
+    ''',
+    unsafe_allow_html=True
+)
+
+with st.sidebar:
+    st.link_button("more_information", "https://www.kaggle.com/code/pankajsinghardh/p-tax-fare")
+st.success("")
+
+model = joblib.load("model.joblib")
+titleimg = "new.jpg"
+
+#impliment background formating
+def set_bg_hack(main_bg):
+    # set bg name
+    main_bg_ext = "jpg"
+    st.markdown(
+        f"""
+         <style>
+         .stApp {{
+             background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()});
+             background-repeat: no-repeat;
+             background-position: right 50% bottom 95% ;
+             background-size: cover;
+             background-attachment: scroll;
+         }}
+         </style>
+         """,
+        unsafe_allow_html=True,
+    )
+
+set_bg_hack(titleimg)
+
+
+
+
+st.markdown("<h1><font color='yellow'><center>'Taxi_Fare'</center></font></h1>",unsafe_allow_html=True)
+le = r'''
+$\textsf{
+    \LARGE Hour\
+}$
+'''
+hour = st.selectbox(f":red[{le}]",range(1,25))
+le = r'''
+$\textsf{
+    \LARGE Distance\
+}$
+'''
+distance = st.number_input(f":red[{le}]",step=1)
+le = r'''
+$\textsf{
+    \LARGE Weekday\
+}$
+'''
+weekday = st.selectbox(f":red[{le}]",["Sunday","Monday","Tuesday","Wednesday","Thursday","Friday","Saturday"])
+
+day = {"Sunday":0,"Monday":1,"Tuesday":3,"Wednesday":4,"Thursday":5,"Friday":6,"Saturday":7}
+btn = st.button("predict")
+if btn:
+    price = model.predict([[hour,distance,day[weekday]]])
+
+    st.snow()
+
+    st.write( ":red[Fare_in_USD]",price)
+    def autoplay_audio(file_path: str):
+        with open(file_path, "rb") as f:
+            data = f.read()
+            b64 = base64.b64encode(data).decode()
+            md = f"""
+                <audio controls autoplay="true">
+                <source src="data:audio/mp3;base64,{b64}" type="audio/mp3">
+                </audio>
+                """
+            st.markdown(
+                md,
+                unsafe_allow_html=True,
+            )
+
+    autoplay_audio("synthesize.mp3")

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e9c4a83be592d763c7872fe23a10c0b16e29a768b072e22e29fa1a66894cf6
+size 4853617

pages/charts.py

@@ -0,0 +1,103 @@
+import pandas as pd
+import streamlit as st
+import base64
+import matplotlib.pyplot as plt
+import seaborn as sns
+import folium
+from streamlit_folium import st_folium
+
+titleimg = "pages\matt.jpg"
+
+#impliment background formating
+def set_bg_hack(main_bg):
+    # set bg name
+    main_bg_ext = "jpg"
+    st.markdown(
+        f"""
+         <style>
+         .stApp {{
+             background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()});
+             background-repeat: no-repeat;
+             background-position: right 50% bottom 95% ;
+             background-size: cover;
+             background-attachment: scroll;
+         }}
+         </style>
+         """,
+        unsafe_allow_html=True,
+    )
+
+set_bg_hack(titleimg)
+
+df = pd.read_csv("pages\TaxiFare.csv", parse_dates=["date_time_of_pickup"])
+
+# from pickup date extract hour information and add new feature to data
+df["hour"] = df.date_time_of_pickup.dt.hour
+
+# from pickup date extract weekday information and add new feature to data
+df["week_day"] = df.date_time_of_pickup.apply(lambda x: x.weekday())
+
+# function for change data into distance in km
+from math import cos, asin, sqrt, pi
+
+
+def distance(lon1, lat1, lon2, lat2):
+    r = 6371  # km
+    p = pi / 180
+
+    a = 0.5 - cos((lat2 - lat1) * p) / 2 + cos(lat1 * p) * cos(lat2 * p) * (1 - cos((lon2 - lon1) * p)) / 2
+    return 2 * r * asin(sqrt(a))
+
+
+# new feature/column for data frame  distance
+data = []
+for x in df.iloc[:, 3:7].values:
+    data.append(round(distance(x[0], x[1], x[2], x[3]), 2))
+
+df["distance"] = data
+
+# from pickup date extract month information and add new feature to data
+df["month"] = df["date_time_of_pickup"].dt.month
+
+
+
+
+# calulating average amount month wise
+st.markdown("<h3><font color='green'><center>Average_Amount_Each_Month</font></center></h3>",unsafe_allow_html=True)
+month_data = df.groupby("month")["amount"].mean().reset_index()
+month_data.index=["januray","february","march","april","may","june","july","august","september","october","november","december"]
+st.bar_chart(month_data,color=["#ffaa11","#ffaa33" ])
+
+
+st.markdown("<h3><font color='green'><center>Average_Amount_Each_Day</font></center></h3>",unsafe_allow_html=True)
+# calculating average amount weekday average amount
+week_data = df.groupby("week_day")["amount"].mean()
+week_data= week_data.reset_index()
+week_data.index=["sunday","monday","tuesday","wednesday","thursday","friday","saturday"]
+
+
+st.bar_chart(week_data)
+
+# grouping data basis on each hour for finding average amount each hour
+st.markdown("<h3><font color='green'><center>Average_Amount_Each_Hour</font></center></h3>",unsafe_allow_html=True)
+hour_data = df.groupby(["hour"])["amount"].mean().reset_index()
+
+st.bar_chart(hour_data)
+
+st.markdown("<h3><font color='green'><center>Correlation matrix</font></center></h3>",unsafe_allow_html=True)
+fig, ax = plt.subplots(figsize=(10,8))
+sns.heatmap(df.iloc[:,1:].corr(), ax=ax,annot=True,cmap="hot")
+st.write(fig)
+st.markdown("""<h4><font color="white">Upon exploring the dataset, no significant correlation was found among the variables. Various correlation measures yielded coefficients close to zero,
+            suggesting a lack of linear relationship between the variables in this dataset. Further analysis utilizing non-linear models or 
+            domain-specific feature engineering may be required to uncover potential dependencies or interactions between the variables.</font></h4>""",unsafe_allow_html=True)
+
+
+
+st.markdown("<h3><font color='green'><center>Pickup Location</font></center></h3>",unsafe_allow_html=True)
+new_york=folium.Map(location=[40.730610, -73.935242], zoom_start=12)
+# polting 100 pickup loction on map
+for i in df.index[:100]:
+    folium.CircleMarker(location=[df['latitude_of_pickup'][i],df['longitude_of_pickup'][i]],color='red').add_to(new_york)
+st_folium(new_york, width=725)
+

pages/data_info.py

@@ -0,0 +1,97 @@
+import pandas as pd
+import streamlit as st
+import base64
+
+
+
+titleimg = "pages\parot.jpg"
+
+#impliment background formating
+def set_bg_hack(main_bg):
+    # set bg name
+    main_bg_ext = "jpg"
+    st.markdown(
+        f"""
+         <style>
+         .stApp {{
+             background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()});
+             background-repeat: no-repeat;
+             background-position: right 50% bottom 95% ;
+             background-size: cover;
+             background-attachment: scroll;
+         }}
+         </style>
+         """,
+        unsafe_allow_html=True,
+    )
+
+set_bg_hack(titleimg)
+
+df = pd.read_csv("pages\TaxiFare.csv", parse_dates=["date_time_of_pickup"])
+
+# from pickup date extract hour information and add new feature to data
+df["hour"] = df.date_time_of_pickup.dt.hour
+
+# from pickup date extract weekday information and add new feature to data
+df["week_day"] = df.date_time_of_pickup.apply(lambda x: x.weekday())
+
+# function for change data into distance in km
+from math import cos, asin, sqrt, pi
+
+
+def distance(lon1, lat1, lon2, lat2):
+    r = 6371  # km
+    p = pi / 180
+
+    a = 0.5 - cos((lat2 - lat1) * p) / 2 + cos(lat1 * p) * cos(lat2 * p) * (1 - cos((lon2 - lon1) * p)) / 2
+    return 2 * r * asin(sqrt(a))
+
+
+# new feature/column for data frame  distance
+data = []
+for x in df.iloc[:, 3:7].values:
+    data.append(round(distance(x[0], x[1], x[2], x[3]), 2))
+
+df["distance"] = data
+
+# from pickup date extract month information and add new feature to data
+df["month"] = df["date_time_of_pickup"].dt.month
+
+
+def data_load(data=df):
+    st.write(":red[Data..]")
+    st.write(data)
+    #st.write(f"{df.info()}")
+
+
+data_load()
+
+
+def data_info():
+    st.write(":red[Descriptive statistics]")
+    st.write(df.describe().T)
+    st.write(":red[Observations]")
+    st.markdown(""" <strong><font color='red' style='bold'><ul style="list-style-type:disc">
+          50,000 entries and 12 columns. 
+         <li><b>1.unique_id:</b> Object type, presumably a unique identifier for each entry.</li>
+         <li><b>2.amount: </b>Floating-point numbers representing some form of monetary value.</li>
+         <li><b>3.date_time_of_pickup:</b> Datetime objects in UTC format, indicating the date and time of pickup.</li>
+         <li><b>4.longitude_of_pickup / latitude_of_pickup: </b>Floating-point numbers representing the coordinates of the pickup location.</li>
+         <li><b>5.longitude_of_dropoff / latitude_of_dropoff:</b> Floating-point numbers representing the coordinates of the drop-off location..</li>
+         <li><b>6.no_of_passenger: </b>Integer values indicating the number of passengers..</li>
+         <li><b>7.hour / week_day / month: </b>Integer values, potentially derived from the datetime, indicating the hour, day of the week, and month, respectively..</li>
+         <li> <b>8.distance:</b> Floating-point numbers representing the distance traveled, likely calculated from coordinates..</li>
+    </ul>
+    The DataFrame seems to contain details of trips or transportation data, presumably with information about fares, locations, timestamps, distances, and passenger counts.
+
+    The memory usage is around 4.2+ MB for this DataFrame, which is moderate given the size of 50,000 entries and the data types used in each column.
+
+    Is there something specific you'd like to know or do with this DataFrame?<p></font></strong>""", unsafe_allow_html=True, )
+
+
+data_info()
+
+
+
+
+

requirements.txt

@@ -0,0 +1,13 @@
+joblib == 1.3.2
+streamlit == 1.31.0
+scikit-learn == 1.2.2
+folium  ==  0.15.1
+numpy  ==  1.26.4
+pandas  == 2.2.0
+streamlit-folium == 0.18.0
+matplotlib ==  3.8.2
+seaborn  ==  0.13.2
+
+
+
+