Create app.py

app.py

@@ -0,0 +1,136 @@
+import gradio as gr
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn import metrics
+from reader import get_article
+
+
+### ------------------------------ ###
+###       data transformation      ###
+### ------------------------------ ###
+# options constants
+options = [
+  ['Very Poorly Aligned', 'Poorly Aligned', 'Neutrally Aligned', 'Well Aligned', 'Very Well Aligned'],
+  ['Very Limited Experience', 'Limited Experience', 'Neutral Experience', 'Extensive Experience', 'Very Extensive Experience'],
+  ['Extremely Unattractive', 'Moderately Unattractive', 'Neutrally Attractive', 'Moderately Attractive', 'Extremely Attractive'],
+  ['Very Unfavorable', 'Moderately Unfavorable', 'Neutrally Favorable', 'Moderately Favorable', 'Very Favorable'],
+  ['Very Poor Fit', 'Poor Fit', 'Neutral Fit', 'Moderately Good Fit', 'Excellent Fit']
+]
+
+# load dataset
+uncleaned_data = pd.read_csv('data.csv')
+data = pd.DataFrame()
+
+# keep track of which columns are categorical and what 
+# those columns' value mappings are
+# structure: {colname1: {...}, colname2: {...} }
+cat_value_dicts = {}
+col = 0
+final_colname = uncleaned_data.columns[4]
+
+# for each column...
+for (colname, colval) in uncleaned_data.iteritems():
+
+  # structure: {0: "lilac", 1: "blue", ...}
+  new_dict = {}
+  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] = options[col].index(item)
+    
+    # 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
+  col += 1
+
+
+### -------------------------------- ###
+###           model training         ###
+### -------------------------------- ###
+
+# select features and predicton; automatically selects last column as prediction
+num_features = 4
+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(max_iter=100)
+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_feats():
+  feats = [abs(x) for x in model.coef_[0]]
+  feats, cols = zip(*sorted(zip(feats, data.columns)))
+
+  output = []
+
+  for idx, col in enumerate(reversed(cols)):
+    output.append(col)
+  
+  # max_val = max(feats)
+  # idx = feats.index(max_val)
+  # return data.columns[idx]
+  return output
+  
+acc = str(round(metrics.accuracy_score(y_test, y_pred) * 100, 2)) + '%'
+feats = get_feats()
+info = get_article(acc, feats)
+
+
+
+### ------------------------------- ###
+###        interface creation       ###
+### ------------------------------- ###
+
+def predictor(*args):
+  features = []
+
+  # transform categorical input
+  for num, col in enumerate(args):
+    features.append(cat_value_dicts[data.columns[num]][col])
+
+  # 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
+inputls = []
+labels = [
+  "How Well Do They Align with RS21's 9 Core Values?",
+  "How Experienced Are They in RS21's Markets?",
+  "How Attractive is Their Valuation of RS21?",
+  "How Favorable is Their Proposed Deal Structure for RS21?"
+]
+
+for num, colname in enumerate(labels):
+
+  # access categories dict if data is categorical
+  inputls.append(gr.inputs.Radio(choices=options[num], type="value", label=labels[num]))
+
+  
+# generate gradio interface
+interface = gr.Interface(predictor, inputs=inputls, outputs="text", article=info['article'], css=info['css'], theme="grass", title=info['title'], allow_flagging='never', description=info['description'])
+
+# show the interface 
+interface.launch()