Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+modified_hotel.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,136 @@
+# import packages and data
+import nltk
+nltk.download('wordnet')
+import numpy as np
+import pandas as pd
+import plotly.express as px
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem.wordnet import WordNetLemmatizer
+from ast import literal_eval
+import streamlit as st
+
+df = pd.read_csv("modified_hotel.csv")
+
+st.title('Hotel Recommendation by Text :compass:')
+st.image('https://www.peninsula.com/en/-/media/news-room/about-us/hkcompany-profile.png?mw=905&hash=3A250365D26358DC9362972842F9321A')
+
+st.write("#### Data Frame")
+st.write("I dropped 30 percent of the original data to fit the file limit, we have 361K rows each accounting and individual comment. with no empty values. Review Dates range from 2015 to 2017.")
+st.dataframe(df)
+
+st.write("The negativity of all the reviews in ascending order. I will drop reviews above 20 negativity.")
+fig = px.histogram(df, x='Review_Total_Negative_Word_Counts')
+st.plotly_chart(fig)
+st.write("The reviewer scores in ascending order. I will drop scores below 8.")
+fig = px.histogram(df, x='Reviewer_Score')
+st.plotly_chart(fig)
+
+st.write("The hotels are from capital cities of 6 countries: Netherlands, United Kingdom, France, Spain, Italy, Austria ")
+st.write("#### Scatter Plot of Latitude vs Longitude")
+fig = px.scatter(df, x="lng", y="lat")
+st.plotly_chart(fig)
+st.write("#### Western Europe Map")
+st.image('https://i.pinimg.com/736x/7b/98/94/7b9894e2f3059e6b1e2fa808516e57b7.jpg')
+
+
+st.write("#### Cleaned Data Frame")
+st.write("We have 190K of good reviews now, with tags and country info ready to process.")
+# drop bad reviews
+df = df[(df['Review_Total_Negative_Word_Counts'] <= 20) & (df['Reviewer_Score'] >= 8)].reset_index(drop=True)
+# Now I will split the address and pick the last word in the address to identify the country
+df["Country"] = df["Hotel_Address"].apply(lambda x: x.split(' ')[-1])
+# Drop unnecessary columns
+df.drop(columns=['Additional_Number_of_Scoring',
+                 'Review_Date',
+                 'Reviewer_Nationality',
+                 'Negative_Review',
+                 'Review_Total_Negative_Word_Counts',
+                 'Total_Number_of_Reviews',
+                 'Positive_Review',
+                 'Review_Total_Positive_Word_Counts',
+                 'Total_Number_of_Reviews_Reviewer_Has_Given',
+                 'Reviewer_Score',
+                 'days_since_review',
+                 'lat',
+                 'lng'], inplace=True)
+# convert the strings of list into a normal list
+def impute(column):
+    column = column[0]
+    if (type(column) != list):
+        return "".join(literal_eval(column))
+    else:
+        return column
+# apply it to the “Tags” column  
+df["Tags"] = df[["Tags"]].apply(impute, axis=1)
+#lowercase 
+df['Country'] = df['Country'].str.lower()
+df['Tags'] = df['Tags'].str.lower()
+country_names = {
+    'kingdom': 'London - UK',
+    'france': 'Paris - France',
+    'netherlands': 'Amsterdam - Netherlands',
+    'spain': 'Madrid - Spain',
+    'italy': 'Rome - Italy',
+    'austria': 'Vienna - Austria',
+}
+df['Country'] = df['Country'].map(country_names)
+st.dataframe(df)
+
+
+#FUNCTION
+def recommend_hotel(location, description):
+    # Lowercase the description and tokenize it
+    description = description.lower()
+    description_tokens = word_tokenize(description)
+
+    # Initialize stopwords and lemmatizer
+    stop_words = set(stopwords.words('english'))
+    lemmatizer = WordNetLemmatizer()
+
+    # Remove stopwords and lemmatize the tokens
+    filtered_tokens = [lemmatizer.lemmatize(token) for token in description_tokens if token not in stop_words]
+
+    # Convert filtered tokens to a set for faster lookup
+    filtered_set = set(filtered_tokens)
+
+    # Filter hotels by location
+    country = df[df['Country'].str.lower() == location.lower()].copy()
+
+    # Compute similarity scores
+    cos = []
+    for tags in country['Tags']:
+        temp_tokens = word_tokenize(tags)
+        temp_filtered = [lemmatizer.lemmatize(token) for token in temp_tokens if token not in stop_words]
+        temp_set = set(temp_filtered)
+        similarity = len(temp_set.intersection(filtered_set))
+        cos.append(similarity)
+
+    # Add similarity scores to DataFrame
+    country['similarity'] = cos
+
+    # Drop duplicates based on hotel name, keeping the highest similarity
+    country.sort_values(by=['Hotel_Name', 'similarity'], ascending=[True, False], inplace=True)
+    country.drop_duplicates(subset='Hotel_Name', keep='first', inplace=True)
+    country.reset_index(drop=True, inplace=True)
+    country.index += 1
+
+    # Select relevant columns and return top recommendations
+    return country[['Hotel_Name', 'Average_Score', 'Hotel_Address']].head(10)
+
+st.write('I have defined my function. Lets use it!')
+st.write('## Europe Hotel Recommendation')
+st.write('Pick a city you are plaining to go and describe what you want. It works like magic! :magic_wand:')
+# Dropdown for location selection
+location = st.selectbox('Select Location', df['Country'].unique())
+#description
+description = st.text_input('Enter Description', "A standard double room for 5 nights for a leisure trip.")
+# Button to trigger recommendation
+if st.button('Find Best Hotels'):
+    recommended_hotels = recommend_hotel(location, description)
+    st.write('### Top 10 Recommended Hotels')
+    st.write(recommended_hotels)
+    st.write('HAVE A GOOD TRIP :wave:')
+
+
+

modified_hotel.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cbce3b7daea0d727fb5fd4840a122dadcf7ae701e0b749dba04592b2164423
+size 166615177

requirements.txt

@@ -0,0 +1,5 @@
+nltk
+numpy
+pandas
+plotly
+wordnet