Data upload

app.py

@@ -0,0 +1,87 @@
+from flask import Flask, render_template, request, url_for, redirect
+from filter import f_country, f_price, filters, price_cat, wine_cat, origin
+import pandas as pd
+
+app = Flask(__name__)
+
+@app.route('/')
+def home():
+    return render_template('home.js')
+
+@app.route('/wine')
+def wine():
+    return render_template('wine.js')
+
+@app.route('/food')
+def food():
+    return render_template('Food.js')
+
+@app.route('/information')
+def information():
+    return render_template('information.js')
+
+@app.route("/button", methods=["POST", "GET"])
+def button():
+    if request.method == "POST":
+        get_country = request.form["nm"]
+        return redirect(url_for("get_country", country=get_country))
+    else:
+	    return render_template('button.html')
+
+@app.route('country/<country>')
+def get_country(country):
+    return f_country(country)
+
+@app.route("/filter", methods=["POST", "GET"])
+def filter():
+    if request.method == "POST":
+        get_filter = request.form["wine"]
+        get_filter = request.form["origin"]
+        return redirect(url_for("get_filter", wine = get_filter, origin = get_filter))
+    else:
+	    return render_template("winefilter.html")
+
+@app.route('/tro/<wine>/<origin>')
+def get_filter(wine, origin):
+    return filters(wine, origin)
+
+@app.route("/category", methods=["POST", "GET"])
+def category():
+    if request.method == "POST":
+        get_winecat = request.form["nm"]
+        return redirect(url_for("get_winecat", wine=get_winecat))
+    else:
+	    return render_template('wine_cat.html')
+
+@app.route("/where", methods=["POST", "GET"])
+def where():
+    if request.method == "POST":
+        get_origin = request.form["nm"]
+        return redirect(url_for("get_origin", name=get_origin))
+    else:
+	    return render_template('wine_cat.html')
+
+@app.route("/price", methods=["POST", "GET"])
+def price():
+    if request.method == "POST":
+        get_pricecat = request.form["nm"]
+        return redirect(url_for("get_pricecat", price=get_pricecat))
+    else:
+	    return render_template('price_cat.html')
+
+@app.route('/pricecat/<price>')
+def get_pricecat(price):
+    return price_cat(price)
+
+@app.route('/origin/<name>')
+def get_origin(name):
+    return origin(name)
+
+@app.route('/winecat/<wine>')
+def get_winecat(wine):
+    return wine_cat(wine)
+
+
+if __name__ == '__main__':
+    app.run(debug=True)
+

data_preaparation.py

@@ -0,0 +1,129 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+wine_data = pd.read_csv('Data/winemag-data-130k-v2.csv.zip', compression='zip', low_memory=False)
+
+print(wine_data.head())
+
+# delete unnecessary columns
+wine_data = wine_data.drop(['Unnamed: 0', 'taster_name', 'taster_twitter_handle', 'region_2'], axis = 1)
+
+# data overview 
+def resumetable(df):
+    print(f"Dataset Shape: {df.shape}")
+    summary = pd.DataFrame(df.dtypes,columns=['dtypes'])
+    summary = summary.reset_index()
+    summary['Name'] = summary['index']
+    summary = summary[['Name','dtypes']]
+    summary['counts'] = df.count().values
+    summary['Missing'] = df.isnull().sum().values
+    summary['missing_ration'] = (df.isnull().sum().values / df.shape[0]) * 100
+    summary['Uniques'] = df.nunique().values
+    return summary
+
+print(resumetable(wine_data))
+
+# drop missing values in certain columns
+wine_data = wine_data.dropna(subset=['price', 'country', 'variety'])
+wine_data = wine_data.drop(['designation'], axis = 1)
+
+# drop double entries based on description and title 
+wine_data = wine_data.drop_duplicates(['description','title'])
+
+wine_data = wine_data.reset_index(drop = True)
+
+print(wine_data.describe())
+
+# transform point system 
+def cat_points(points):
+    if points in list(range(80,83)):
+        return 0
+    elif points in list(range(83,87)):
+        return 1
+    elif points in list(range(87,90)):
+        return 2
+    elif points in list(range(90,94)):
+        return 3
+    elif points in list(range(94,98)):
+        return 4
+    else:
+        return 5
+
+wine_data["rating"] = wine_data["points"].apply(cat_points)
+
+wine_data = wine_data.drop(['points'], axis = 1)
+
+# assign different varieties to categories of wine
+conditions_wine = [
+    (wine_data['variety'].str.contains('Sauvignon Blanc')) | (wine_data['variety'].str.contains('Pinot Grigio')) | (wine_data['variety'].str.contains('Albariño')) | (wine_data['variety'].str.contains('Pino Gris')),
+    (wine_data['variety'].str.contains('Gewürztraminer'))  | (wine_data['variety'].str.contains('Malvasia')) | (wine_data['variety'].str.contains('Moscato')) | (wine_data['variety'].str.contains('Riesling')),
+    (wine_data['variety'].str.contains('Chardonnay')) | (wine_data['variety'].str.contains('Viognier')) | (wine_data['variety'].str.contains('Roussanne')) | (wine_data['variety'].str.contains('Marsanne')),
+    (wine_data['variety'].str.contains('Champagne')) | (wine_data['variety'].str.contains('Prosecco')) | (wine_data['variety'].str.contains('Sparkling')) | (wine_data['variety'].str.contains('Cava')),
+    (wine_data['variety'].str.contains('St. Laurent')) | (wine_data['variety'].str.contains('Gamay')) | (wine_data['variety'].str.contains('Pinot Noir')) | (wine_data['variety'].str.contains('Zweigelt')),
+    (wine_data['variety'].str.contains('Red Table Wine')) | (wine_data['variety'].str.contains('Zinfandel')) | (wine_data['variety'].str.contains('Merlot')),
+    (wine_data['variety'].str.contains('Cabernet Sauvignon')) | (wine_data['variety'].str.contains('Malbec')) | (wine_data['variety'].str.contains('Anglianico')) | (wine_data['variety'].str.contains('Syrah')) | (wine_data['variety'].str.contains('Sangiovese')) | (wine_data['variety'].str.contains('Carbanet Franc')),
+    (wine_data['variety'].str.contains('Late Harvest')) | (wine_data['variety'] == 'Port') | (wine_data['variety'].str.contains('Ice Wine')) | (wine_data['variety'].str.contains('Sherry')),
+    (wine_data['variety'].str.contains('Rosé'))]
+
+# categories of wine
+values_wine = ['dry white wine', 'sweet white wine', 'rich white wine', 'sparkling wine', 'light red wine', 'medium red wine', 'bold red wine', 'dessert wine', 'rosé']
+
+wine_data['wine_categories'] = np.select(conditions_wine, values_wine)
+
+# not all data can be assigned to categorie 
+# variety with largest amount of different sorts of wine in this dataset are assigned manually 
+variety_u_null = wine_data[wine_data['wine_categories'] == '0']
+variety_u_null_g = variety_u_null.groupby('variety')['variety'].count()
+v_sort = variety_u_null_g.sort_values(ascending = False)
+
+# price categories 
+price = wine_data.price
+price = price.sort_values(ascending = False)
+summe = price.sum()
+price = pd.DataFrame(price)
+price['perci'] = price/summe
+price['perci_c'] = price['perci'].cumsum()
+FFF = price[price['perci_c'] <= 0.15]
+FF = price[(price['perci_c'] > 0.15) & (price['perci_c'] <= 0.87)]
+F = price[price['perci_c'] > 0.87]
+
+conditions_price = [
+    (wine_data['price'] >= 101),
+    (wine_data['price'] < 101) & (wine_data['price'] >= 21),
+    (wine_data['price'] < 21)
+    ]
+
+# price categories: 4 is most expensive 
+values_price = [3, 2, 1]
+
+wine_data['price_cat'] = np.select(conditions_price, values_price)
+
+# food link
+conditions_food = [
+    (wine_data['wine_categories'] == 'dry white wine'),
+    (wine_data['wine_categories'] == 'sweet white wine'),
+    (wine_data['wine_categories'] == 'rich white wine'),
+    (wine_data['wine_categories'] == 'sparkling wine'),
+    (wine_data['wine_categories'] == 'light red wine'),
+    (wine_data['wine_categories'] == 'medium red wine'),
+    (wine_data['wine_categories'] == 'bold red wine'),
+    (wine_data['wine_categories'] == 'desert wine'),
+    (wine_data['wine_categories'] == 'rosé')]
+
+values_food = ['vegetables, roasted vegetables, starches, fish', 
+          'soft cheese, hard cheese, cured meat, sweets',
+          'soft cheese, starches, fish, rich fish, white meat',
+          'vegetables, soft cheese, hard cheese, starches, fish',
+          'roasted vegetables, starches, rich fish, white meat, cured meat',
+          'roasted vegetables, hard cheese, starches, white meat, red meat, cured meat',
+          'hard cheese, starches, red meat, cured meat', 
+          'soft cheese, starches, cured meat, sweets',
+          'everything']
+
+wine_data['food'] = np.select(conditions_food, values_food)
+
+wine_data_food = wine_data[wine_data['food'] != '0']
+wine_data_food = wine_data_food.reset_index(drop = True)
+
+wine_data_food_f = wine_data_food.drop(['description'], axis = 1)

filter.py

@@ -0,0 +1,133 @@
+import pandas as pd
+import numpy as np
+
+wine_data = pd.read_csv('Data/wine_food_data_f.csv', low_memory=False)
+
+
+def f_country(country: str):
+    wine_data = pd.read_csv('data/wine_food_data.csv', low_memory=False)
+    selection_c = wine_data[wine_data['country'] == country]
+    result_c = selection_c[['country', 'title', 'price', 'rating']]
+    result_c_p = result_c.to_dict()
+    return result_c_p
+
+# filter wine categorie
+def wine_cat(wine = 'red'):
+    cat_result = wine_data[wine_data['wine_categories'].str.contains(wine)]
+    output_dict_c = cat_result.transpose().to_dict()
+    return output_dict_c
+
+# filter origin 
+def origin(name):
+    wine_data = pd.read_csv('data/wine_food_data.csv', low_memory=False)
+    if name == 'europe':
+        return wine_data[(wine_data['country'] == 'Spain') 
+                         | (wine_data['country'] == 'Portugal') 
+                         | (wine_data['country'] == 'France') 
+                         | (wine_data['country'] == 'Germany') 
+                         | (wine_data['country'] == 'Italy') 
+                         | (wine_data['country'] == 'Romania') 
+                         | (wine_data['country'] == 'Austria')
+                         | (wine_data['country'] == 'Slovenia')
+                         | (wine_data['country'] == 'Croatia')
+                         | (wine_data['country'] == 'England')
+                         | (wine_data['country'] == 'Czech Republic')
+                         | (wine_data['country'] == 'Bulgaria')
+                         | (wine_data['country'] == 'Greece')
+                         | (wine_data['country'] == 'Turkey')
+                         | (wine_data['country'] == 'Moldova')
+                         | (wine_data['country'] == 'Hungary')
+                         | (wine_data['country'] == 'Switzerland')
+                         | (wine_data['country'] == 'Ukraine')
+                         | (wine_data['country'] == 'Slovakia')
+                         | (wine_data['country'] == 'Serbia')
+                         | (wine_data['country'] == 'Luxembourg')
+                         | (wine_data['country'] == 'Macedonia')].transpose().to_dict()
+    elif name == 'national':
+        return wine_data[wine_data['country'] == 'Germany'].transpose().to_dict()
+    elif name == 'international':
+        return wine_data[(wine_data['country'] == 'Mexico') 
+                         | (wine_data['country'] == 'China') 
+                         | (wine_data['country'] == 'US') 
+                         | (wine_data['country'] == 'Argentina') 
+                         | (wine_data['country'] == 'Chile') 
+                         | (wine_data['country'] == 'Australia') 
+                         | (wine_data['country'] == 'South Africa') 
+                         | (wine_data['country'] == 'New Zealand') 
+                         | (wine_data['country'] == 'Israel')
+                         | (wine_data['country'] == 'Canada')
+                         | (wine_data['country'] == 'Lebanon')
+                         | (wine_data['country'] == 'Brazil')
+                         | (wine_data['country'] == 'Morocco')
+                         | (wine_data['country'] == 'Uruguay')
+                         | (wine_data['country'] == 'Peru')
+                         | (wine_data['country'] == 'India')
+                         | (wine_data['country'] == 'Georgia')
+                         | (wine_data['country'] == 'Armenia')].transpose().to_dict()
+
+
+# filter price category 
+def price_cat(price = 1):
+    selection = wine_data[wine_data['price_cat'] == price]
+    result_p = selection.sort_values('price')
+    result_p = result_p.transpose().to_dict()
+    return result_p
+
+
+
+# filter together
+def filters(wine, origin):
+    if wine in ['red', 'white', 'rosé']:
+        wine_cat = wine_data[wine_data['wine_categories'].str.contains(wine)]
+    else: 
+        wine_cat = wine_data
+
+    if origin == 'europe':
+        wine_o = wine_cat[(wine_cat['country'] == 'Spain') 
+                         | (wine_cat['country'] == 'Portugal') 
+                         | (wine_cat['country'] == 'France') 
+                         | (wine_cat['country'] == 'Germany') 
+                         | (wine_cat['country'] == 'Italy') 
+                         | (wine_cat['country'] == 'Romania') 
+                         | (wine_cat['country'] == 'Austria')
+                         | (wine_cat['country'] == 'Slovenia')
+                         | (wine_cat['country'] == 'Croatia')
+                         | (wine_cat['country'] == 'England')
+                         | (wine_cat['country'] == 'Czech Republic')
+                         | (wine_cat['country'] == 'Bulgaria')
+                         | (wine_cat['country'] == 'Greece')
+                         | (wine_cat['country'] == 'Turkey')
+                         | (wine_cat['country'] == 'Moldova')
+                         | (wine_cat['country'] == 'Hungary')
+                         | (wine_cat['country'] == 'Switzerland')
+                         | (wine_cat['country'] == 'Ukraine')
+                         | (wine_cat['country'] == 'Slovakia')
+                         | (wine_cat['country'] == 'Serbia')
+                         | (wine_cat['country'] == 'Luxembourg')
+                         | (wine_cat['country'] == 'Macedonia')]
+    elif origin == 'national':
+        wine_o = wine_cat[wine_cat['country'] == 'Germany']
+    elif origin == 'international':
+        wine_o =  wine_cat[(wine_cat['country'] == 'Mexico') 
+                         | (wine_cat['country'] == 'China') 
+                         | (wine_cat['country'] == 'US') 
+                         | (wine_cat['country'] == 'Argentina') 
+                         | (wine_cat['country'] == 'Chile') 
+                         | (wine_cat['country'] == 'Australia') 
+                         | (wine_cat['country'] == 'South Africa') 
+                         | (wine_cat['country'] == 'New Zealand') 
+                         | (wine_cat['country'] == 'Israel')
+                         | (wine_cat['country'] == 'Canada')
+                         | (wine_cat['country'] == 'Lebanon')
+                         | (wine_cat['country'] == 'Brazil')
+                         | (wine_cat['country'] == 'Morocco')
+                         | (wine_cat['country'] == 'Uruguay')
+                         | (wine_cat['country'] == 'Peru')
+                         | (wine_cat['country'] == 'India')
+                         | (wine_cat['country'] == 'Georgia')
+                         | (wine_cat['country'] == 'Armenia')]
+    else:
+        wine_o = wine_cat
+
+    output = wine_o.transpose().to_dict()
+    return output

templates/Food.js

@@ -0,0 +1,9 @@
+import React from 'react';
+
+const Food = () => {
+  return <div>
+    <h1>what matches your food?</h1>
+  </div>;
+};
+
+export default Food;

templates/base.html

@@ -0,0 +1,11 @@
+<!doctype html>
+
+<html lang="en">
+<head>
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1">
+</head>
+<body>
+  {% block body %}{% endblock %}
+</body>
+</html>

templates/button.html

@@ -0,0 +1,9 @@
+{% block title %}Button{% endblock %}
+
+{% block content %}
+<form action="#" method="post">
+	<p>Infos:</p>
+	<p><input type="text" name="nm" /></p>
+	<p><input type="submit" value="submit"/></p>
+</form>
+{% endblock %}