Upload 4 files

app (1).py

@@ -0,0 +1,172 @@
+### ----------------------------- ###
+###           libraries           ###
+### ----------------------------- ###
+
+import gradio as gr
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn import metrics
+
+
+### ------------------------------ ###
+###       data transformation      ###
+### ------------------------------ ###
+
+# load dataset
+uncleaned_data = pd.read_csv('data.csv')
+
+# remove timestamp from dataset (always first column)
+uncleaned_data = uncleaned_data.iloc[: , 1:]
+data = pd.DataFrame()
+
+# keep track of which columns are categorical and what 
+# those columns' value mappings are
+# structure: {colname1: {...}, colname2: {...} }
+cat_value_dicts = {}
+final_colname = uncleaned_data.columns[len(uncleaned_data.columns) - 1]
+
+# for each column...
+for (colname, colval) in uncleaned_data.iteritems():
+
+  # check if col is already a number; if so, add col directly
+  # to new dataframe and skip to next column
+  if isinstance(colval.values[0], (np.integer, float)):
+    data[colname] = uncleaned_data[colname].copy()
+    continue
+
+  # structure: {0: "lilac", 1: "blue", ...}
+  new_dict = {}
+  val = 0 # first index per column
+  transformed_col_vals = [] # new numeric datapoints
+
+  # if not, for each item in that column...
+  for (row, item) in enumerate(colval.values):
+    
+    # if item is not in this col's dict...
+    if item not in new_dict:
+      new_dict[item] = val
+      val += 1
+    
+    # then add numerical value to transformed dataframe
+    transformed_col_vals.append(new_dict[item])
+  
+  # reverse dictionary only for final col (0, 1) => (vals)
+  if colname == final_colname:
+    new_dict = {value : key for (key, value) in new_dict.items()}
+
+  cat_value_dicts[colname] = new_dict
+  data[colname] = transformed_col_vals
+
+
+### -------------------------------- ###
+###           model training         ###
+### -------------------------------- ###
+
+# select features and predicton; automatically selects last column as prediction
+cols = len(data.columns)
+num_features = cols - 1
+x = data.iloc[: , :num_features]
+y = data.iloc[: , num_features:]
+
+# split data into training and testing sets
+x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
+
+# instantiate the model (using default parameters)
+model = LogisticRegression()
+model.fit(x_train, y_train.values.ravel())
+y_pred = model.predict(x_test)
+
+
+### -------------------------------- ###
+###        article generation        ###
+### -------------------------------- ###
+# borrow file reading function from reader.py
+
+def get_feat():
+  feats = [abs(x) for x in model.coef_[0]]
+  max_val = max(feats)
+  idx = feats.index(max_val)
+  return data.columns[idx]
+  
+acc = str(round(metrics.accuracy_score(y_test, y_pred) * 100, 1)) + "%"
+most_imp_feat = get_feat()
+# info = get_article(acc, most_imp_feat)
+
+
+
+### ------------------------------- ###
+###        interface creation       ###
+### ------------------------------- ###
+
+
+# predictor for generic number of features
+def general_predictor(*args):
+  features = []
+
+  # transform categorical input
+  for colname, arg in zip(data.columns, args):
+    if (colname in cat_value_dicts):
+      features.append(cat_value_dicts[colname][arg])
+    else:
+      features.append(arg)
+
+  # predict single datapoint
+  new_input = [features]
+  result = model.predict(new_input)
+  return cat_value_dicts[final_colname][result[0]]
+
+# add data labels to replace those lost via star-args
+
+
+block = gr.Blocks()
+
+with open('info.md') as f:
+  with block:
+    gr.Markdown(f.readline())
+    gr.Markdown('Take the quiz to get a personalized recommendation using AI.')
+    
+    with gr.Row():
+      with gr.Group():
+        inputls = []
+        for colname in data.columns:
+          # skip last column
+          if colname == final_colname:
+            continue
+          
+          # access categories dict if data is categorical
+          # otherwise, just use a number input
+          if colname in cat_value_dicts:
+            radio_options = list(cat_value_dicts[colname].keys())
+            inputls.append(gr.Dropdown(radio_options, type="value", label=colname))
+          else:
+            # add numerical input
+            inputls.append(gr.Number(label=colname))
+          gr.Markdown("<br />")
+        
+        submit = gr.Button("Click to see your personalized result!", variant="primary")
+        gr.Markdown("<br />")
+        output = gr.Textbox(label="Your recommendation:", placeholder="your recommendation will appear here")
+        
+        submit.click(fn=general_predictor, inputs=inputls, outputs=output)
+        gr.Markdown("<br />")
+        
+        with gr.Row():
+          with gr.Group():
+            gr.Markdown(f"<h3>Accuracy: </h3>{acc}")
+          with gr.Group():
+            gr.Markdown(f"<h3>Most important feature: </h3>{most_imp_feat}")
+        
+        gr.Markdown("<br />")
+        
+        with gr.Group():
+          gr.Markdown('''⭐ Note that model accuracy is based on the uploaded data.csv and reflects how well the AI model can give correct recommendations for <em>that dataset</em>. Model accuracy and most important feature can be helpful for understanding how the model works, but <em>should not be considered absolute facts about the real world</em>.''')
+        
+      with gr.Group():
+        with open('info.md') as f:
+          f.readline()
+          gr.Markdown(f.read())
+
+# show the interface
+block.launch()

data.csv

@@ -0,0 +1,16 @@
+Timestamp,"Which year group are you in?
+","Have you ever tried watching a Korean drama?
+",Q3: Do you have a favorite Korean actor or actress?,"Do you cry easily?
+","Are you an easy-going person?
+",Do you have friends who are really into K-drama?,How do you feel about subtitles?,"Do you prefer shows with many episodes or shorter series?
+","Are you interested in K-dramas that showcase Korean culture or modern Korean society?
+","Are you okay with a slow-paced drama focusing on character development?
+",Which type of storyline appeals to you more?
+9/2/2024 13:46:05,D: Y10,"C: No, never","C: No, I don’t like anyone",C: Depends,C: Maybe,"A: Yes, a lot of my friends love it",C: I'd like a mix of both.,A: A lot of episodes (20+),B: Not necessarily; I just want a good story.,"A: Yes, I love character-driven stories.",F: A crime/mystery story with investigative elements.
+9/2/2024 13:50:36,D: Y10,"C: No, never","C: No, I don’t like anyone",C: Depends,C: Maybe,"B: Yes, but only a few friends",C: I'd like a mix of both.,A: A lot of episodes (20+),B: Not necessarily; I just want a good story.,"B: No, I prefer a faster-paced plot.","C: A fun, light-hearted comedy."
+9/2/2024 19:23:25,D: Y10,"C: No, never","D: No, but I heard someone before",B: No,A: Yes,"A: Yes, a lot of my friends love it",C: I'd like a mix of both.,B: Shorter series (12-16 episodes),B: Not necessarily; I just want a good story.,"B: No, I prefer a faster-paced plot.",D: A story set in a different historical or fantasy world.
+9/5/2024 10:33:20,D: Y10,"C: No, never","C: No, I don’t like anyone",C: Depends,C: Maybe,"B: Yes, but only a few friends",A: I love them. I don't mind reading while watching.,A: A lot of episodes (20+),B: Not necessarily; I just want a good story.,"A: Yes, I love character-driven stories.",A: A heartwarming romance with emotional depth.
+9/17/2024 15:58:28,D: Y10,"C: No, never","C: No, I don’t like anyone",B: No,B: No,"B: Yes, but only a few friends",B: I prefer dubbed versions.,B: Shorter series (12-16 episodes),B: Not necessarily; I just want a good story.,"A: Yes, I love character-driven stories.",E: A drama centered on family and friendships.
+9/17/2024 18:44:50,D: Y10,"B: Yes, I watched a lot","A: Yes, I watched their series",A: Yes,C: Maybe,"B: Yes, but only a few friends",A: I love them. I don't mind reading while watching.,B: Shorter series (12-16 episodes),B: Not necessarily; I just want a good story.,"B: No, I prefer a faster-paced plot.",F: A crime/mystery story with investigative elements.
+9/17/2024 19:34:50,D: Y10,"A: Yes, but not much","D: No, but I heard someone before",C: Depends,A: Yes,"B: Yes, but only a few friends",A: I love them. I don't mind reading while watching.,A: A lot of episodes (20+),B: Not necessarily; I just want a good story.,"A: Yes, I love character-driven stories.",B: A fast-paced thriller with lots of twists.
+9/17/2024 22:30:03,D: Y10,"A: Yes, but not much","D: No, but I heard someone before",B: No,C: Maybe,"A: Yes, a lot of my friends love it",A: I love them. I don't mind reading while watching.,B: Shorter series (12-16 episodes),C: A little bit of both.,"A: Yes, I love character-driven stories.",F: A crime/mystery story with investigative elements.

info.md

@@ -0,0 +1,16 @@
+# 😌 [Edit info.md - Your app's title here]
+
+### 🧐 Problem Statement and Research Summary
+[add info about your problem statement and your research here!]
+
+### 🎣 Data Collection Plan
+[Edit info.md - add info about what data you collected and why here!]
+
+### 💥 Ethical Considerations (Data Privacy and Bias)
+* Data privacy: [Edit info.md - add info about you considered users' privacy here!]
+* Bias: [Edit info.md - add info about you considered bias here!]
+
+### 👻 Our Team
+[Edit info.md - add info about your team members here!]
+
+![aiEDU logo](https://images.squarespace-cdn.com/content/v1/5e4efdef6d10420691f02bc1/5db5a8a3-1761-4fce-a096-bd5f2515162f/aiEDU+_black+logo+stacked.png?format=100w)

requirements.txt

@@ -0,0 +1,4 @@
+pip>=23.2.1
+pandas==1.3.4
+scikit-learn>=1.0.1
+numpy==1.21.4