Update app.py

app.py

@@ -4,10 +4,10 @@ st.set_page_config(f'SDSN x GIZ Policy Tracing', layout="wide")
 import seaborn as sns
 import pdfplumber
 from pandas import DataFrame
-from keybert import KeyBERT
 import matplotlib.pyplot as plt
 import numpy as np
 import streamlit as st
+import sentence-transformers
 
 
 
@@ -68,11 +68,121 @@ with st.expander("ℹ️ - About this app", expanded=True):
 
 st.markdown("")
 st.markdown("")
-st.markdown("##  📌 Step One: Upload document ")
+#st.markdown("##  📌 Step One: Upload document ")
 
 
 with st.container():
     st.markdown("##  📌 Step One: Upload document ")
     ##file = st.file_uploader('Upload PDF File', type=['pdf'])
     text_str = read_(file)
-    
+    
+    
+import seaborn as sns
+import pdfplumber
+from pandas import DataFrame
+from keybert import KeyBERT
+import matplotlib.pyplot as plt
+import numpy as np
+import streamlit as st
+
+
+
+    @st.cache(allow_output_mutation=True)
+    def load_model():
+        return KeyBERT()
+
+    kw_model = load_model()
+
+    keywords = kw_model.extract_keywords(
+    text_str,
+    keyphrase_ngram_range=(1, 2),
+    use_mmr=True,
+    stop_words="english",
+    top_n=10,
+    diversity=0.7,
+    )
+
+    st.markdown("## 🎈 What is my document about?")
+
+    df = (
+        DataFrame(keywords, columns=["Keyword/Keyphrase", "Relevancy"])
+        .sort_values(by="Relevancy", ascending=False)
+        .reset_index(drop=True)
+    )
+
+    df.index += 1
+
+    # Add styling
+    cmGreen = sns.light_palette("green", as_cmap=True)
+    cmRed = sns.light_palette("red", as_cmap=True)
+    df = df.style.background_gradient(
+        cmap=cmGreen,
+        subset=[
+            "Relevancy",
+        ],
+    )
+    c1, c2, c3 = st.columns([1, 3, 1])
+
+    format_dictionary = {
+        "Relevancy": "{:.1%}",
+    }
+
+    df = df.format(format_dictionary)
+
+    with c2:
+        st.table(df) 
+
+    ######## SDG!
+    from transformers import pipeline 
+
+    finetuned_checkpoint = "jonas/sdg_classifier_osdg"
+    classifier = pipeline("text-classification", model=finetuned_checkpoint)
+
+    word_list = text_str.split()
+    len_word_list = len(word_list)
+    par_list = []
+    par_len = 130
+    for i in range(0,len_word_list // par_len):
+        string_part = ' '.join(word_list[i*par_len:(i+1)*par_len])
+        par_list.append(string_part)
+        
+    labels = classifier(par_list)
+    labels_= [(l['label'],l['score']) for l in labels]
+    df = DataFrame(labels_, columns=["SDG", "Relevancy"])
+    df['text'] = ['... '+par+' ...' for par in par_list]      
+    df = df.sort_values(by="Relevancy", ascending=False).reset_index(drop=True)  
+    df.index += 1
+    df =df[df['Relevancy']>.9]
+    x = df['SDG'].value_counts()
+
+    plt.rcParams['font.size'] = 25
+    colors = plt.get_cmap('Blues')(np.linspace(0.2, 0.7, len(x)))
+    # plot
+    fig, ax = plt.subplots()
+    ax.pie(x, colors=colors, radius=2, center=(4, 4),
+         wedgeprops={"linewidth": 1, "edgecolor": "white"}, frame=False,labels =list(x.index))
+
+    st.markdown("## 🎈 Anything related to SDGs?")
+
+    c4, c5, c6 = st.columns([5, 7, 1])
+
+    # Add styling
+    cmGreen = sns.light_palette("green", as_cmap=True)
+    cmRed = sns.light_palette("red", as_cmap=True)
+    df = df.style.background_gradient(
+        cmap=cmGreen,
+        subset=[
+            "Relevancy",
+        ],
+    )
+
+    format_dictionary = {
+        "Relevancy": "{:.1%}",
+    }
+
+    df = df.format(format_dictionary)
+
+    with c4:
+        st.pyplot(fig)
+    with c5:
+        st.table(df)