Upload 4 files

app.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 +1,11 @@
+Timestamp,"If you have the day off, would you like to","When you speed time with people, at you often feel","When planning events, how likely are you to invite someone?",People say you are,You are better at talking with
+7/29/2025 9:20:28,Stay home,Neutral but enjoyed the compony,Some what likely,too informational,Anyone
+7/29/2025 9:23:56,meet up with a friend,Neutral but enjoyed the compony,Extremally likely,too informational,one and ones for new people
+7/29/2025 9:24:35,meet up with a friend,Neutral but enjoyed the compony,Extremally likely,districted,close friends
+7/29/2025 9:26:24,go or make a party,Neutral but enjoyed the compony,Some what likely,reserved,close friends
+7/29/2025 9:26:59,meet up with a friend,Neutral but still need to recharged,Some what likely,reserved,close friends
+7/29/2025 9:27:00,meet up with a friend,Neutral but enjoyed the compony,Most not likely,districted,close friends
+7/29/2025 9:27:21,go to the park alone,Neutral but still need to recharged,Not likely,reserved,one and ones for new people
+7/29/2025 9:30:45,Stay home,Neutral but still need to recharged,Some what likely,districted,close friends
+7/29/2025 9:46:00,meet up with a friend,Neutral but enjoyed the compony,Extremally likely,too talkative,Anyone
+7/29/2025 9:56:50,Stay home,Neutral but still need to recharged,Some what likely,too informational,close friends

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