Modify the overall framework and improve the first function

requirements.txt

@@ -0,0 +1,74 @@
+annotated-types==0.6.0
+archspec @ file:///croot/archspec_1697725767277/work
+blis==0.7.11
+boltons @ file:///Users/cbousseau/work/recipes/ci_py311/boltons_1677965141748/work
+Brotli @ file:///Users/cbousseau/work/recipes/ci_py311/brotli-split_1677936346777/work
+catalogue==2.0.10
+certifi @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_35eq66o3mo/croot/certifi_1700501684871/work/certifi
+cffi @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_b4nang6w_y/croot/cffi_1700254307954/work
+charset-normalizer @ file:///tmp/build/80754af9/charset-normalizer_1630003229654/work
+click==8.1.7
+cloudpathlib==0.16.0
+conda @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_a2jidg4a7u/croot/conda_1706737968110/work
+conda-content-trust @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_5324skqvu9/croot/conda-content-trust_1693490622873/work
+conda-libmamba-solver @ file:///croot/conda-libmamba-solver_1702997573971/work/src
+conda-package-handling @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_fc4cx8vjhj/croot/conda-package-handling_1690999937094/work
+conda_package_streaming @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_aecpaup22q/croot/conda-package-streaming_1690987978274/work
+confection==0.1.4
+cryptography @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_b1p0q5vizk/croot/cryptography_1702070293829/work
+cymem==2.0.8
+distro @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_10ye1wu827/croot/distro_1701455019085/work
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl#sha256=86cc141f63942d4b2c5fcee06630fd6f904788d2f0ab005cce45aadb8fb73889
+flashtext==2.7
+gensim==4.3.2
+geographiclib @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_bb1rwz0oji/croot/geographiclib_1683807319323/work
+idna @ file:///Users/cbousseau/work/recipes/ci_py311/idna_1677906072337/work
+Jinja2==3.1.3
+joblib==1.3.2
+jsonpatch @ file:///tmp/build/80754af9/jsonpatch_1615747632069/work
+jsonpointer==2.1
+langcodes==3.3.0
+libmambapy @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_59l2npsw_8/croot/mamba-split_1698782625405/work/libmambapy
+MarkupSafe==2.1.5
+menuinst @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_a2fxmxkg_z/croot/menuinst_1702390297906/work
+murmurhash==1.0.10
+numpy==1.26.4
+packaging @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_6dm6d4jd_t/croot/packaging_1693575176524/work
+pandas==2.2.0
+patsy==0.5.6
+platformdirs @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_a8u4fy8k9o/croot/platformdirs_1692205661656/work
+pluggy @ file:///Users/cbousseau/work/recipes/ci_py311/pluggy_1677906980825/work
+preshed==3.0.9
+pycosat @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_3eg8vdcs6z/croot/pycosat_1696536519213/work
+pycparser @ file:///tmp/build/80754af9/pycparser_1636541352034/work
+pydantic==2.6.1
+pydantic_core==2.16.2
+pyOpenSSL @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_b8whqav6qm/croot/pyopenssl_1690223428943/work
+PySocks @ file:///Users/cbousseau/work/recipes/ci_py311/pysocks_1677906386870/work
+python-dateutil==2.8.2
+pytz==2024.1
+requests @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_54zi68h2nb/croot/requests_1690400233316/work
+ruamel.yaml @ file:///Users/cbousseau/work/recipes/ci_py311/ruamel.yaml_1677934845850/work
+scattertext==0.2.0
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+six==1.16.0
+smart-open==6.4.0
+spacy==3.7.4
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+statsmodels==0.14.1
+streamlit
+thinc==8.2.3
+threadpoolctl==3.3.0
+tqdm @ file:///private/var/folders/nz/j6p8yfhx1mv_0grj5xl4650h0000gp/T/abs_ac7zic_tin/croot/tqdm_1679561870178/work
+truststore @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_42mm7e6j06/croot/truststore_1695244298716/work
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2024.1
+urllib3 @ file:///private/var/folders/k1/30mswbxs7r1g6zwn8y4fyt500000gp/T/abs_068obtb882/croot/urllib3_1698257558009/work
+wasabi==1.1.2
+weasel==0.3.4
+zstandard @ file:///Users/cbousseau/work/recipes/ci_py311_2/zstandard_1678996192313/work
+https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.7.1/en_core_web_md-3.7.1.tar.gz

scattertext_funtion.py

@@ -3,12 +3,12 @@ import streamlit as st
 import scattertext as stx
 import spacy
 import pandas as pd
-import en_core_web_sm
+import en_core_web_md
 
 
 
 # load language model:
-nlp = en_core_web_sm.load()
+nlp = en_core_web_md.load()
 nlp = spacy.load("en_core_web_md")
 
 # config
@@ -16,22 +16,23 @@ st.title("Scattertext Analysis")
 # TODO：update other web settings
 
 # upload file
+
+
+# read data
 uploaded_file = st.file_uploader("Upload your text document", type=["csv", "txt"])
 # proceed data
 if uploaded_file is not None:
-    if uploaded_file.name.endswith(".csv"):
-        df = pd.read_csv(uploaded_file)
-    elif uploaded_file.name.endswith(".txt"):
-        df = pd.read_csv(uploaded_file, sep='\t')
-        # TODO: check, assume contents are seperated by Tabs.
-# choose function
-    function_choice = st.selectbox('Choose function', ('Choose...', 'Generate Scattertext Plot', '...'))
-    # TODO: add new functions here (paper sections)
-# define function1
-    if function_choice == 'Generate Scattertext Plot':
-        text_columns = df.select_dtypes(include=['object']).columns.tolist()
-        chosen_column = st.selectbox("Choose text column for analysis", text_columns)
-        if st.button('Generate Scattertext Plot'):
+    # choose function
+    function_choice = st.selectbox('Choose file source', ('Choose...', 'Customized', 'Download from Online Databases'))
+    # function1: generate plot from customized file
+    if st.button('Customized'):
+        if uploaded_file.name.endswith(".csv"):
+            df = pd.read_csv(uploaded_file)
+        elif uploaded_file.name.endswith(".txt"):
+            df = pd.read_csv(uploaded_file, sep='\t')  # TODO : doc: assume contents are seperated by Tabs.
+
+            text_columns = df.select_dtypes(include=['object']).columns.tolist()
+            chosen_column = st.selectbox("Choose text column for analysis", text_columns)
             # convert to scattertext corpus
             corpus = stx.CorpusFromPandas(
                 text_columns,
@@ -53,7 +54,8 @@ if uploaded_file is not None:
                                        minimum_term_frequency=0,
                                        metadata=df)
         st.components.v1.html(html)
-# TODO: insert new functions
+
+
 
     else:
         st.error("Unsupported file format.")